{
  "status": "COMPLETE_26_DECISION_PLUS_3_LLM_REFERENCES_1342",
  "question_count": 1342,
  "model_count": 29,
  "primary_cases": 38918,
  "family_count": 31,
  "ranked_model_ids": [
    "reference_sol",
    "mammoth1",
    "drex_max",
    "respan02",
    "pplx_decider12",
    "nimble_v4_max",
    "d3_turbo",
    "liquid_ultra",
    "amos_large",
    "reference_sonnet",
    "kettei_fat",
    "jev114",
    "jev113",
    "mercury_decide",
    "elephant1",
    "reference_qwen",
    "liquid_d1",
    "clef",
    "pplx_flash12",
    "microsoft_decision",
    "drex20",
    "clef_flash",
    "clef_omni",
    "drex15",
    "kev4b",
    "luna_decisions",
    "tev1_4b_native",
    "classify1",
    "solar_flash"
  ],
  "models": {
    "respan02": {
      "n": 1342,
      "correct": 1127,
      "answered": 1342,
      "wrong_valid": 215,
      "failed": 0,
      "accuracy": 0.8397913561847988,
      "accuracy_among_usable": 0.8397913561847988,
      "eventual": {
        "n": 1342,
        "correct": 1127,
        "answered": 1342,
        "wrong_valid": 215,
        "failed": 0,
        "accuracy": 0.8397913561847988,
        "accuracy_among_usable": 0.8397913561847988
      },
      "median_ms": 205.52456245059147,
      "p95_ms": 2157.423888955964,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "model_output_failures": 0,
      "probability_warnings": 0,
      "cost": {
        "known_usd": 0.00474628,
        "known_decimal": "0.00474628",
        "unknown_attempts": 0,
        "exact_usd": 0.00474628,
        "cost_sources": {
          "api_reported": 1342
        },
        "known_usd_per_1000": 0.00353672131147541
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 796,
          "correct": 755,
          "answered": 796,
          "wrong_valid": 41,
          "failed": 0,
          "accuracy": 0.9484924623115578,
          "accuracy_among_usable": 0.9484924623115578
        },
        "0.9": {
          "n": 712,
          "correct": 684,
          "answered": 712,
          "wrong_valid": 28,
          "failed": 0,
          "accuracy": 0.9606741573033708,
          "accuracy_among_usable": 0.9606741573033708
        },
        "0.95": {
          "n": 629,
          "correct": 612,
          "answered": 629,
          "wrong_valid": 17,
          "failed": 0,
          "accuracy": 0.972972972972973,
          "accuracy_among_usable": 0.972972972972973
        }
      },
      "latency_first_usable": {
        "n": 1342,
        "median_ms": 205.52456245059147,
        "p95_ms": 2157.423888955964
      },
      "provider_failures": 0,
      "dates_toronto": {
        "2026-10-18": 1136,
        "2026-10-19": 206
      },
      "returned_identities": {
        "respan/span-02-20261015": 1342
      },
      "providers": {
        "Respan": 1342
      },
      "model_id": "respan02",
      "label": "Respan Span-02",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 39,
          "answered": 43,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9069767441860465,
          "accuracy_among_usable": 0.9069767441860465
        },
        "F02": {
          "n": 46,
          "correct": 32,
          "answered": 46,
          "wrong_valid": 14,
          "failed": 0,
          "accuracy": 0.6956521739130435,
          "accuracy_among_usable": 0.6956521739130435
        },
        "F03": {
          "n": 52,
          "correct": 44,
          "answered": 52,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.8461538461538461,
          "accuracy_among_usable": 0.8461538461538461
        },
        "F04": {
          "n": 54,
          "correct": 50,
          "answered": 54,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9259259259259259,
          "accuracy_among_usable": 0.9259259259259259
        },
        "F05": {
          "n": 49,
          "correct": 43,
          "answered": 49,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.8775510204081632,
          "accuracy_among_usable": 0.8775510204081632
        },
        "F06": {
          "n": 40,
          "correct": 38,
          "answered": 40,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.95,
          "accuracy_among_usable": 0.95
        },
        "F07": {
          "n": 76,
          "correct": 58,
          "answered": 76,
          "wrong_valid": 18,
          "failed": 0,
          "accuracy": 0.7631578947368421,
          "accuracy_among_usable": 0.7631578947368421
        },
        "F08": {
          "n": 67,
          "correct": 63,
          "answered": 67,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9402985074626866,
          "accuracy_among_usable": 0.9402985074626866
        },
        "F09": {
          "n": 71,
          "correct": 46,
          "answered": 71,
          "wrong_valid": 25,
          "failed": 0,
          "accuracy": 0.647887323943662,
          "accuracy_among_usable": 0.647887323943662
        },
        "F10": {
          "n": 74,
          "correct": 55,
          "answered": 74,
          "wrong_valid": 19,
          "failed": 0,
          "accuracy": 0.7432432432432432,
          "accuracy_among_usable": 0.7432432432432432
        },
        "F11": {
          "n": 41,
          "correct": 36,
          "answered": 41,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8780487804878049,
          "accuracy_among_usable": 0.8780487804878049
        },
        "F12": {
          "n": 52,
          "correct": 28,
          "answered": 52,
          "wrong_valid": 24,
          "failed": 0,
          "accuracy": 0.5384615384615384,
          "accuracy_among_usable": 0.5384615384615384
        },
        "F13": {
          "n": 48,
          "correct": 33,
          "answered": 48,
          "wrong_valid": 15,
          "failed": 0,
          "accuracy": 0.6875,
          "accuracy_among_usable": 0.6875
        },
        "F14": {
          "n": 42,
          "correct": 40,
          "answered": 42,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.9523809523809523,
          "accuracy_among_usable": 0.9523809523809523
        },
        "F15": {
          "n": 49,
          "correct": 42,
          "answered": 49,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.8571428571428571,
          "accuracy_among_usable": 0.8571428571428571
        },
        "F16": {
          "n": 50,
          "correct": 42,
          "answered": 50,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.84,
          "accuracy_among_usable": 0.84
        },
        "F17": {
          "n": 50,
          "correct": 41,
          "answered": 50,
          "wrong_valid": 9,
          "failed": 0,
          "accuracy": 0.82,
          "accuracy_among_usable": 0.82
        },
        "F18": {
          "n": 50,
          "correct": 47,
          "answered": 50,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.94,
          "accuracy_among_usable": 0.94
        },
        "F19": {
          "n": 58,
          "correct": 53,
          "answered": 58,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.9137931034482759,
          "accuracy_among_usable": 0.9137931034482759
        },
        "F20": {
          "n": 43,
          "correct": 39,
          "answered": 43,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9069767441860465,
          "accuracy_among_usable": 0.9069767441860465
        },
        "F21": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9302325581395349,
          "accuracy_among_usable": 0.9302325581395349
        },
        "F22": {
          "n": 51,
          "correct": 49,
          "answered": 51,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.9607843137254902,
          "accuracy_among_usable": 0.9607843137254902
        },
        "F23": {
          "n": 52,
          "correct": 51,
          "answered": 52,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9807692307692307,
          "accuracy_among_usable": 0.9807692307692307
        },
        "F24": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8837209302325582,
          "accuracy_among_usable": 0.8837209302325582
        },
        "F25": {
          "n": 50,
          "correct": 46,
          "answered": 50,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.92,
          "accuracy_among_usable": 0.92
        },
        "F26": {
          "n": 8,
          "correct": 6,
          "answered": 8,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.75,
          "accuracy_among_usable": 0.75
        },
        "F27": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F28": {
          "n": 8,
          "correct": 8,
          "answered": 8,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        },
        "F29": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F30": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F31": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        }
      },
      "macro_family_accuracy": 0.8244083125467018,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 1112,
        "answered": 1305,
        "wrong_valid": 193,
        "failed": 0,
        "accuracy": 0.8521072796934865,
        "accuracy_among_usable": 0.8521072796934865
      },
      "new_domains": {
        "n": 48,
        "correct": 34,
        "answered": 48,
        "wrong_valid": 14,
        "failed": 0,
        "accuracy": 0.7083333333333334,
        "accuracy_among_usable": 0.7083333333333334
      }
    },
    "pplx_decider12": {
      "n": 1342,
      "correct": 1120,
      "answered": 1341,
      "wrong_valid": 221,
      "failed": 1,
      "accuracy": 0.834575260804769,
      "accuracy_among_usable": 0.8351976137211037,
      "eventual": {
        "n": 1342,
        "correct": 1121,
        "answered": 1342,
        "wrong_valid": 221,
        "failed": 0,
        "accuracy": 0.8353204172876304,
        "accuracy_among_usable": 0.8353204172876304
      },
      "median_ms": 249.11764601711184,
      "p95_ms": 332.19568336498935,
      "attempts": 1343,
      "recoveries": 1,
      "first_statuses": {
        "ok": 1341,
        "provider_failure": 1
      },
      "model_output_failures": 0,
      "probability_warnings": 0,
      "cost": {
        "known_usd": 0.00939382,
        "known_decimal": "0.00939382",
        "unknown_attempts": 1,
        "exact_usd": null,
        "cost_sources": {
          "api_reported": 1342,
          "unreported": 1
        },
        "known_usd_per_1000": 0.006999865871833086
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 940,
          "correct": 931,
          "answered": 940,
          "wrong_valid": 9,
          "failed": 0,
          "accuracy": 0.9904255319148936,
          "accuracy_among_usable": 0.9904255319148936
        },
        "0.9": {
          "n": 886,
          "correct": 884,
          "answered": 886,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.9977426636568849,
          "accuracy_among_usable": 0.9977426636568849
        },
        "0.95": {
          "n": 855,
          "correct": 854,
          "answered": 855,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9988304093567252,
          "accuracy_among_usable": 0.9988304093567252
        }
      },
      "latency_first_usable": {
        "n": 1341,
        "median_ms": 249.14037506096065,
        "p95_ms": 332.33487501274794
      },
      "provider_failures": 1,
      "dates_toronto": {
        "2026-10-18": 1136,
        "2026-10-19": 206
      },
      "returned_identities": {
        "perplexity/pplx-decider-v1.2-20261016": 1341,
        "unreported (error)": 1
      },
      "providers": {
        "Perplexity": 1341,
        "unreported": 1
      },
      "model_id": "pplx_decider12",
      "label": "Perplexity Decider v1.2",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9302325581395349,
          "accuracy_among_usable": 0.9302325581395349
        },
        "F02": {
          "n": 46,
          "correct": 45,
          "answered": 46,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9782608695652174,
          "accuracy_among_usable": 0.9782608695652174
        },
        "F03": {
          "n": 52,
          "correct": 50,
          "answered": 52,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.9615384615384616,
          "accuracy_among_usable": 0.9615384615384616
        },
        "F04": {
          "n": 54,
          "correct": 48,
          "answered": 54,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.8888888888888888,
          "accuracy_among_usable": 0.8888888888888888
        },
        "F05": {
          "n": 49,
          "correct": 44,
          "answered": 49,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8979591836734694,
          "accuracy_among_usable": 0.8979591836734694
        },
        "F06": {
          "n": 40,
          "correct": 38,
          "answered": 40,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.95,
          "accuracy_among_usable": 0.95
        },
        "F07": {
          "n": 76,
          "correct": 54,
          "answered": 76,
          "wrong_valid": 22,
          "failed": 0,
          "accuracy": 0.7105263157894737,
          "accuracy_among_usable": 0.7105263157894737
        },
        "F08": {
          "n": 67,
          "correct": 65,
          "answered": 67,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.9701492537313433,
          "accuracy_among_usable": 0.9701492537313433
        },
        "F09": {
          "n": 71,
          "correct": 43,
          "answered": 71,
          "wrong_valid": 28,
          "failed": 0,
          "accuracy": 0.6056338028169014,
          "accuracy_among_usable": 0.6056338028169014
        },
        "F10": {
          "n": 74,
          "correct": 58,
          "answered": 74,
          "wrong_valid": 16,
          "failed": 0,
          "accuracy": 0.7837837837837838,
          "accuracy_among_usable": 0.7837837837837838
        },
        "F11": {
          "n": 41,
          "correct": 37,
          "answered": 41,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9024390243902439,
          "accuracy_among_usable": 0.9024390243902439
        },
        "F12": {
          "n": 52,
          "correct": 33,
          "answered": 52,
          "wrong_valid": 19,
          "failed": 0,
          "accuracy": 0.6346153846153846,
          "accuracy_among_usable": 0.6346153846153846
        },
        "F13": {
          "n": 48,
          "correct": 14,
          "answered": 48,
          "wrong_valid": 34,
          "failed": 0,
          "accuracy": 0.2916666666666667,
          "accuracy_among_usable": 0.2916666666666667
        },
        "F14": {
          "n": 42,
          "correct": 39,
          "answered": 42,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9285714285714286,
          "accuracy_among_usable": 0.9285714285714286
        },
        "F15": {
          "n": 49,
          "correct": 35,
          "answered": 49,
          "wrong_valid": 14,
          "failed": 0,
          "accuracy": 0.7142857142857143,
          "accuracy_among_usable": 0.7142857142857143
        },
        "F16": {
          "n": 50,
          "correct": 36,
          "answered": 50,
          "wrong_valid": 14,
          "failed": 0,
          "accuracy": 0.72,
          "accuracy_among_usable": 0.72
        },
        "F17": {
          "n": 50,
          "correct": 46,
          "answered": 50,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.92,
          "accuracy_among_usable": 0.92
        },
        "F18": {
          "n": 50,
          "correct": 46,
          "answered": 50,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.92,
          "accuracy_among_usable": 0.92
        },
        "F19": {
          "n": 58,
          "correct": 54,
          "answered": 58,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9310344827586207,
          "accuracy_among_usable": 0.9310344827586207
        },
        "F20": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8837209302325582,
          "accuracy_among_usable": 0.8837209302325582
        },
        "F21": {
          "n": 43,
          "correct": 42,
          "answered": 43,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9767441860465116,
          "accuracy_among_usable": 0.9767441860465116
        },
        "F22": {
          "n": 51,
          "correct": 47,
          "answered": 50,
          "wrong_valid": 3,
          "failed": 1,
          "accuracy": 0.9215686274509803,
          "accuracy_among_usable": 0.94
        },
        "F23": {
          "n": 52,
          "correct": 52,
          "answered": 52,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        },
        "F24": {
          "n": 43,
          "correct": 42,
          "answered": 43,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9767441860465116,
          "accuracy_among_usable": 0.9767441860465116
        },
        "F25": {
          "n": 50,
          "correct": 48,
          "answered": 50,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.96,
          "accuracy_among_usable": 0.96
        },
        "F26": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F27": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F28": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F29": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F30": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F31": {
          "n": 8,
          "correct": 6,
          "answered": 8,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.75,
          "accuracy_among_usable": 0.75
        }
      },
      "macro_family_accuracy": 0.793818185451345,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 1105,
        "answered": 1304,
        "wrong_valid": 199,
        "failed": 1,
        "accuracy": 0.8467432950191571,
        "accuracy_among_usable": 0.8473926380368099
      },
      "new_domains": {
        "n": 48,
        "correct": 26,
        "answered": 48,
        "wrong_valid": 22,
        "failed": 0,
        "accuracy": 0.5416666666666666,
        "accuracy_among_usable": 0.5416666666666666
      }
    },
    "nimble_v4_max": {
      "n": 1342,
      "correct": 1115,
      "answered": 1342,
      "wrong_valid": 227,
      "failed": 0,
      "accuracy": 0.830849478390462,
      "accuracy_among_usable": 0.830849478390462,
      "eventual": {
        "n": 1342,
        "correct": 1115,
        "answered": 1342,
        "wrong_valid": 227,
        "failed": 0,
        "accuracy": 0.830849478390462,
        "accuracy_among_usable": 0.830849478390462
      },
      "median_ms": 235.37189594935626,
      "p95_ms": 328.7085750023835,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "model_output_failures": 0,
      "probability_warnings": 0,
      "cost": {
        "known_usd": 0.03708378,
        "known_decimal": "0.03708378",
        "unknown_attempts": 0,
        "exact_usd": 0.03708378,
        "cost_sources": {
          "usage_times_published_tariff": 1134,
          "usage_times_current_published_tariff": 2,
          "usage_times_captured_tariff": 206
        },
        "known_usd_per_1000": 0.02763321907600596
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 837,
          "correct": 836,
          "answered": 837,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.998805256869773,
          "accuracy_among_usable": 0.998805256869773
        },
        "0.9": {
          "n": 760,
          "correct": 760,
          "answered": 760,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        },
        "0.95": {
          "n": 685,
          "correct": 685,
          "answered": 685,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        }
      },
      "latency_first_usable": {
        "n": 1342,
        "median_ms": 235.37189594935626,
        "p95_ms": 328.7085750023835
      },
      "provider_failures": 0,
      "dates_toronto": {
        "2026-10-16": 1134,
        "2026-10-18": 2,
        "2026-10-19": 206
      },
      "returned_identities": {
        "nimble-v4-max": 1342
      },
      "providers": {
        "unreported": 1342
      },
      "model_id": "nimble_v4_max",
      "label": "Nimble v4 Max",
      "route": "Bespoke direct",
      "families": {
        "F01": {
          "n": 43,
          "correct": 41,
          "answered": 43,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.9534883720930233,
          "accuracy_among_usable": 0.9534883720930233
        },
        "F02": {
          "n": 46,
          "correct": 45,
          "answered": 46,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9782608695652174,
          "accuracy_among_usable": 0.9782608695652174
        },
        "F03": {
          "n": 52,
          "correct": 49,
          "answered": 52,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9423076923076923,
          "accuracy_among_usable": 0.9423076923076923
        },
        "F04": {
          "n": 54,
          "correct": 50,
          "answered": 54,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9259259259259259,
          "accuracy_among_usable": 0.9259259259259259
        },
        "F05": {
          "n": 49,
          "correct": 45,
          "answered": 49,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9183673469387755,
          "accuracy_among_usable": 0.9183673469387755
        },
        "F06": {
          "n": 40,
          "correct": 38,
          "answered": 40,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.95,
          "accuracy_among_usable": 0.95
        },
        "F07": {
          "n": 76,
          "correct": 51,
          "answered": 76,
          "wrong_valid": 25,
          "failed": 0,
          "accuracy": 0.6710526315789473,
          "accuracy_among_usable": 0.6710526315789473
        },
        "F08": {
          "n": 67,
          "correct": 60,
          "answered": 67,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.8955223880597015,
          "accuracy_among_usable": 0.8955223880597015
        },
        "F09": {
          "n": 71,
          "correct": 39,
          "answered": 71,
          "wrong_valid": 32,
          "failed": 0,
          "accuracy": 0.5492957746478874,
          "accuracy_among_usable": 0.5492957746478874
        },
        "F10": {
          "n": 74,
          "correct": 53,
          "answered": 74,
          "wrong_valid": 21,
          "failed": 0,
          "accuracy": 0.7162162162162162,
          "accuracy_among_usable": 0.7162162162162162
        },
        "F11": {
          "n": 41,
          "correct": 32,
          "answered": 41,
          "wrong_valid": 9,
          "failed": 0,
          "accuracy": 0.7804878048780488,
          "accuracy_among_usable": 0.7804878048780488
        },
        "F12": {
          "n": 52,
          "correct": 35,
          "answered": 52,
          "wrong_valid": 17,
          "failed": 0,
          "accuracy": 0.6730769230769231,
          "accuracy_among_usable": 0.6730769230769231
        },
        "F13": {
          "n": 48,
          "correct": 19,
          "answered": 48,
          "wrong_valid": 29,
          "failed": 0,
          "accuracy": 0.3958333333333333,
          "accuracy_among_usable": 0.3958333333333333
        },
        "F14": {
          "n": 42,
          "correct": 41,
          "answered": 42,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9761904761904762,
          "accuracy_among_usable": 0.9761904761904762
        },
        "F15": {
          "n": 49,
          "correct": 36,
          "answered": 49,
          "wrong_valid": 13,
          "failed": 0,
          "accuracy": 0.7346938775510204,
          "accuracy_among_usable": 0.7346938775510204
        },
        "F16": {
          "n": 50,
          "correct": 38,
          "answered": 50,
          "wrong_valid": 12,
          "failed": 0,
          "accuracy": 0.76,
          "accuracy_among_usable": 0.76
        },
        "F17": {
          "n": 50,
          "correct": 46,
          "answered": 50,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.92,
          "accuracy_among_usable": 0.92
        },
        "F18": {
          "n": 50,
          "correct": 45,
          "answered": 50,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.9,
          "accuracy_among_usable": 0.9
        },
        "F19": {
          "n": 58,
          "correct": 57,
          "answered": 58,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9827586206896551,
          "accuracy_among_usable": 0.9827586206896551
        },
        "F20": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9302325581395349,
          "accuracy_among_usable": 0.9302325581395349
        },
        "F21": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9302325581395349,
          "accuracy_among_usable": 0.9302325581395349
        },
        "F22": {
          "n": 51,
          "correct": 49,
          "answered": 51,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.9607843137254902,
          "accuracy_among_usable": 0.9607843137254902
        },
        "F23": {
          "n": 52,
          "correct": 52,
          "answered": 52,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        },
        "F24": {
          "n": 43,
          "correct": 42,
          "answered": 43,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9767441860465116,
          "accuracy_among_usable": 0.9767441860465116
        },
        "F25": {
          "n": 50,
          "correct": 47,
          "answered": 50,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.94,
          "accuracy_among_usable": 0.94
        },
        "F26": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F27": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F28": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F29": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F30": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F31": {
          "n": 8,
          "correct": 6,
          "answered": 8,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.75,
          "accuracy_among_usable": 0.75
        }
      },
      "macro_family_accuracy": 0.7898861893259329,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 1099,
        "answered": 1305,
        "wrong_valid": 206,
        "failed": 0,
        "accuracy": 0.8421455938697318,
        "accuracy_among_usable": 0.8421455938697318
      },
      "new_domains": {
        "n": 48,
        "correct": 25,
        "answered": 48,
        "wrong_valid": 23,
        "failed": 0,
        "accuracy": 0.5208333333333334,
        "accuracy_among_usable": 0.5208333333333334
      }
    },
    "jev114": {
      "n": 1342,
      "correct": 1030,
      "answered": 1342,
      "wrong_valid": 312,
      "failed": 0,
      "accuracy": 0.767511177347243,
      "accuracy_among_usable": 0.767511177347243,
      "eventual": {
        "n": 1342,
        "correct": 1030,
        "answered": 1342,
        "wrong_valid": 312,
        "failed": 0,
        "accuracy": 0.767511177347243,
        "accuracy_among_usable": 0.767511177347243
      },
      "median_ms": 179.4867084827274,
      "p95_ms": 268.8569815829396,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "model_output_failures": 0,
      "probability_warnings": 17,
      "cost": {
        "known_usd": 0.03297441,
        "known_decimal": "0.032974410",
        "unknown_attempts": 0,
        "exact_usd": 0.03297441,
        "cost_sources": {
          "recorded_accounted_or_reported": 1134,
          "api_reported": 208
        },
        "known_usd_per_1000": 0.024571095380029807
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 740,
          "correct": 728,
          "answered": 740,
          "wrong_valid": 12,
          "failed": 0,
          "accuracy": 0.9837837837837838,
          "accuracy_among_usable": 0.9837837837837838
        },
        "0.9": {
          "n": 668,
          "correct": 664,
          "answered": 668,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9940119760479041,
          "accuracy_among_usable": 0.9940119760479041
        },
        "0.95": {
          "n": 614,
          "correct": 613,
          "answered": 614,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.998371335504886,
          "accuracy_among_usable": 0.998371335504886
        }
      },
      "latency_first_usable": {
        "n": 1342,
        "median_ms": 179.4867084827274,
        "p95_ms": 268.8569815829396
      },
      "provider_failures": 0,
      "dates_toronto": {
        "2026-10-15": 1134,
        "2026-10-18": 2,
        "2026-10-19": 206
      },
      "returned_identities": {
        "typesafe/jev-1.14-20261014": 1342
      },
      "providers": {
        "TypeSafe": 1342
      },
      "model_id": "jev114",
      "label": "Jev 1.14",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 39,
          "answered": 43,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9069767441860465,
          "accuracy_among_usable": 0.9069767441860465
        },
        "F02": {
          "n": 46,
          "correct": 46,
          "answered": 46,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        },
        "F03": {
          "n": 52,
          "correct": 48,
          "answered": 52,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9230769230769231,
          "accuracy_among_usable": 0.9230769230769231
        },
        "F04": {
          "n": 54,
          "correct": 49,
          "answered": 54,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.9074074074074074,
          "accuracy_among_usable": 0.9074074074074074
        },
        "F05": {
          "n": 49,
          "correct": 46,
          "answered": 49,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9387755102040817,
          "accuracy_among_usable": 0.9387755102040817
        },
        "F06": {
          "n": 40,
          "correct": 38,
          "answered": 40,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.95,
          "accuracy_among_usable": 0.95
        },
        "F07": {
          "n": 76,
          "correct": 48,
          "answered": 76,
          "wrong_valid": 28,
          "failed": 0,
          "accuracy": 0.631578947368421,
          "accuracy_among_usable": 0.631578947368421
        },
        "F08": {
          "n": 67,
          "correct": 57,
          "answered": 67,
          "wrong_valid": 10,
          "failed": 0,
          "accuracy": 0.8507462686567164,
          "accuracy_among_usable": 0.8507462686567164
        },
        "F09": {
          "n": 71,
          "correct": 28,
          "answered": 71,
          "wrong_valid": 43,
          "failed": 0,
          "accuracy": 0.39436619718309857,
          "accuracy_among_usable": 0.39436619718309857
        },
        "F10": {
          "n": 74,
          "correct": 39,
          "answered": 74,
          "wrong_valid": 35,
          "failed": 0,
          "accuracy": 0.527027027027027,
          "accuracy_among_usable": 0.527027027027027
        },
        "F11": {
          "n": 41,
          "correct": 32,
          "answered": 41,
          "wrong_valid": 9,
          "failed": 0,
          "accuracy": 0.7804878048780488,
          "accuracy_among_usable": 0.7804878048780488
        },
        "F12": {
          "n": 52,
          "correct": 30,
          "answered": 52,
          "wrong_valid": 22,
          "failed": 0,
          "accuracy": 0.5769230769230769,
          "accuracy_among_usable": 0.5769230769230769
        },
        "F13": {
          "n": 48,
          "correct": 7,
          "answered": 48,
          "wrong_valid": 41,
          "failed": 0,
          "accuracy": 0.14583333333333334,
          "accuracy_among_usable": 0.14583333333333334
        },
        "F14": {
          "n": 42,
          "correct": 40,
          "answered": 42,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.9523809523809523,
          "accuracy_among_usable": 0.9523809523809523
        },
        "F15": {
          "n": 49,
          "correct": 34,
          "answered": 49,
          "wrong_valid": 15,
          "failed": 0,
          "accuracy": 0.6938775510204082,
          "accuracy_among_usable": 0.6938775510204082
        },
        "F16": {
          "n": 50,
          "correct": 34,
          "answered": 50,
          "wrong_valid": 16,
          "failed": 0,
          "accuracy": 0.68,
          "accuracy_among_usable": 0.68
        },
        "F17": {
          "n": 50,
          "correct": 44,
          "answered": 50,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.88,
          "accuracy_among_usable": 0.88
        },
        "F18": {
          "n": 50,
          "correct": 38,
          "answered": 50,
          "wrong_valid": 12,
          "failed": 0,
          "accuracy": 0.76,
          "accuracy_among_usable": 0.76
        },
        "F19": {
          "n": 58,
          "correct": 48,
          "answered": 58,
          "wrong_valid": 10,
          "failed": 0,
          "accuracy": 0.8275862068965517,
          "accuracy_among_usable": 0.8275862068965517
        },
        "F20": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8837209302325582,
          "accuracy_among_usable": 0.8837209302325582
        },
        "F21": {
          "n": 43,
          "correct": 42,
          "answered": 43,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9767441860465116,
          "accuracy_among_usable": 0.9767441860465116
        },
        "F22": {
          "n": 51,
          "correct": 48,
          "answered": 51,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9411764705882353,
          "accuracy_among_usable": 0.9411764705882353
        },
        "F23": {
          "n": 52,
          "correct": 49,
          "answered": 52,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9423076923076923,
          "accuracy_among_usable": 0.9423076923076923
        },
        "F24": {
          "n": 43,
          "correct": 37,
          "answered": 43,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.8604651162790697,
          "accuracy_among_usable": 0.8604651162790697
        },
        "F25": {
          "n": 50,
          "correct": 45,
          "answered": 50,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.9,
          "accuracy_among_usable": 0.9
        },
        "F26": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F27": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F28": {
          "n": 8,
          "correct": 2,
          "answered": 8,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F29": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F30": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F31": {
          "n": 8,
          "correct": 6,
          "answered": 8,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.75,
          "accuracy_among_usable": 0.75
        }
      },
      "macro_family_accuracy": 0.7445631724514891,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 1014,
        "answered": 1305,
        "wrong_valid": 291,
        "failed": 0,
        "accuracy": 0.7770114942528735,
        "accuracy_among_usable": 0.7770114942528735
      },
      "new_domains": {
        "n": 48,
        "correct": 26,
        "answered": 48,
        "wrong_valid": 22,
        "failed": 0,
        "accuracy": 0.5416666666666666,
        "accuracy_among_usable": 0.5416666666666666
      }
    },
    "liquid_ultra": {
      "n": 1342,
      "correct": 1084,
      "answered": 1341,
      "wrong_valid": 257,
      "failed": 1,
      "accuracy": 0.8077496274217586,
      "accuracy_among_usable": 0.808351976137211,
      "eventual": {
        "n": 1342,
        "correct": 1085,
        "answered": 1342,
        "wrong_valid": 257,
        "failed": 0,
        "accuracy": 0.8084947839046199,
        "accuracy_among_usable": 0.8084947839046199
      },
      "median_ms": 200.17650042427704,
      "p95_ms": 393.4226100856908,
      "attempts": 1343,
      "recoveries": 1,
      "first_statuses": {
        "ok": 1341,
        "provider_failure": 1
      },
      "model_output_failures": 0,
      "probability_warnings": 0,
      "cost": {
        "known_usd": 0.016270002,
        "known_decimal": "0.016270002",
        "unknown_attempts": 1,
        "exact_usd": null,
        "cost_sources": {
          "api_reported": 1342,
          "unreported": 1
        },
        "known_usd_per_1000": 0.012123697466467957
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 839,
          "correct": 835,
          "answered": 839,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9952324195470799,
          "accuracy_among_usable": 0.9952324195470799
        },
        "0.9": {
          "n": 774,
          "correct": 772,
          "answered": 774,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.9974160206718347,
          "accuracy_among_usable": 0.9974160206718347
        },
        "0.95": {
          "n": 707,
          "correct": 706,
          "answered": 707,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9985855728429985,
          "accuracy_among_usable": 0.9985855728429985
        }
      },
      "latency_first_usable": {
        "n": 1341,
        "median_ms": 200.2075839554891,
        "p95_ms": 393.87520798482
      },
      "provider_failures": 1,
      "dates_toronto": {
        "2026-10-18": 1136,
        "2026-10-19": 206
      },
      "returned_identities": {
        "liquid/d1-ultra-20261015": 1341,
        "unreported (error)": 1
      },
      "providers": {
        "Liquid": 1341,
        "unreported": 1
      },
      "model_id": "liquid_ultra",
      "label": "Liquid d1-ultra",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 41,
          "answered": 43,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.9534883720930233,
          "accuracy_among_usable": 0.9534883720930233
        },
        "F02": {
          "n": 46,
          "correct": 44,
          "answered": 46,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.9565217391304348,
          "accuracy_among_usable": 0.9565217391304348
        },
        "F03": {
          "n": 52,
          "correct": 50,
          "answered": 52,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.9615384615384616,
          "accuracy_among_usable": 0.9615384615384616
        },
        "F04": {
          "n": 54,
          "correct": 51,
          "answered": 54,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9444444444444444,
          "accuracy_among_usable": 0.9444444444444444
        },
        "F05": {
          "n": 49,
          "correct": 45,
          "answered": 49,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9183673469387755,
          "accuracy_among_usable": 0.9183673469387755
        },
        "F06": {
          "n": 40,
          "correct": 39,
          "answered": 40,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.975,
          "accuracy_among_usable": 0.975
        },
        "F07": {
          "n": 76,
          "correct": 57,
          "answered": 76,
          "wrong_valid": 19,
          "failed": 0,
          "accuracy": 0.75,
          "accuracy_among_usable": 0.75
        },
        "F08": {
          "n": 67,
          "correct": 55,
          "answered": 67,
          "wrong_valid": 12,
          "failed": 0,
          "accuracy": 0.8208955223880597,
          "accuracy_among_usable": 0.8208955223880597
        },
        "F09": {
          "n": 71,
          "correct": 42,
          "answered": 71,
          "wrong_valid": 29,
          "failed": 0,
          "accuracy": 0.5915492957746479,
          "accuracy_among_usable": 0.5915492957746479
        },
        "F10": {
          "n": 74,
          "correct": 46,
          "answered": 73,
          "wrong_valid": 27,
          "failed": 1,
          "accuracy": 0.6216216216216216,
          "accuracy_among_usable": 0.6301369863013698
        },
        "F11": {
          "n": 41,
          "correct": 35,
          "answered": 41,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.8536585365853658,
          "accuracy_among_usable": 0.8536585365853658
        },
        "F12": {
          "n": 52,
          "correct": 27,
          "answered": 52,
          "wrong_valid": 25,
          "failed": 0,
          "accuracy": 0.5192307692307693,
          "accuracy_among_usable": 0.5192307692307693
        },
        "F13": {
          "n": 48,
          "correct": 11,
          "answered": 48,
          "wrong_valid": 37,
          "failed": 0,
          "accuracy": 0.22916666666666666,
          "accuracy_among_usable": 0.22916666666666666
        },
        "F14": {
          "n": 42,
          "correct": 38,
          "answered": 42,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9047619047619048,
          "accuracy_among_usable": 0.9047619047619048
        },
        "F15": {
          "n": 49,
          "correct": 38,
          "answered": 49,
          "wrong_valid": 11,
          "failed": 0,
          "accuracy": 0.7755102040816326,
          "accuracy_among_usable": 0.7755102040816326
        },
        "F16": {
          "n": 50,
          "correct": 34,
          "answered": 50,
          "wrong_valid": 16,
          "failed": 0,
          "accuracy": 0.68,
          "accuracy_among_usable": 0.68
        },
        "F17": {
          "n": 50,
          "correct": 45,
          "answered": 50,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.9,
          "accuracy_among_usable": 0.9
        },
        "F18": {
          "n": 50,
          "correct": 40,
          "answered": 50,
          "wrong_valid": 10,
          "failed": 0,
          "accuracy": 0.8,
          "accuracy_among_usable": 0.8
        },
        "F19": {
          "n": 58,
          "correct": 57,
          "answered": 58,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9827586206896551,
          "accuracy_among_usable": 0.9827586206896551
        },
        "F20": {
          "n": 43,
          "correct": 39,
          "answered": 43,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9069767441860465,
          "accuracy_among_usable": 0.9069767441860465
        },
        "F21": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9302325581395349,
          "accuracy_among_usable": 0.9302325581395349
        },
        "F22": {
          "n": 51,
          "correct": 47,
          "answered": 51,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9215686274509803,
          "accuracy_among_usable": 0.9215686274509803
        },
        "F23": {
          "n": 52,
          "correct": 51,
          "answered": 52,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9807692307692307,
          "accuracy_among_usable": 0.9807692307692307
        },
        "F24": {
          "n": 43,
          "correct": 42,
          "answered": 43,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9767441860465116,
          "accuracy_among_usable": 0.9767441860465116
        },
        "F25": {
          "n": 50,
          "correct": 45,
          "answered": 50,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.9,
          "accuracy_among_usable": 0.9
        },
        "F26": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F27": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F28": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F29": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F30": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F31": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        }
      },
      "macro_family_accuracy": 0.7703162855657344,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 1071,
        "answered": 1304,
        "wrong_valid": 233,
        "failed": 1,
        "accuracy": 0.8206896551724138,
        "accuracy_among_usable": 0.821319018404908
      },
      "new_domains": {
        "n": 48,
        "correct": 25,
        "answered": 48,
        "wrong_valid": 23,
        "failed": 0,
        "accuracy": 0.5208333333333334,
        "accuracy_among_usable": 0.5208333333333334
      }
    },
    "mercury_decide": {
      "n": 1342,
      "correct": 1017,
      "answered": 1342,
      "wrong_valid": 325,
      "failed": 0,
      "accuracy": 0.7578241430700448,
      "accuracy_among_usable": 0.7578241430700448,
      "eventual": {
        "n": 1342,
        "correct": 1017,
        "answered": 1342,
        "wrong_valid": 325,
        "failed": 0,
        "accuracy": 0.7578241430700448,
        "accuracy_among_usable": 0.7578241430700448
      },
      "median_ms": 238.4314374648966,
      "p95_ms": 388.3725829655305,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "model_output_failures": 0,
      "probability_warnings": 0,
      "cost": {
        "known_usd": 0.00933446,
        "known_decimal": "0.00933446",
        "unknown_attempts": 0,
        "exact_usd": 0.00933446,
        "cost_sources": {
          "api_reported": 1342
        },
        "known_usd_per_1000": 0.006955633383010432
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 972,
          "correct": 873,
          "answered": 972,
          "wrong_valid": 99,
          "failed": 0,
          "accuracy": 0.8981481481481481,
          "accuracy_among_usable": 0.8981481481481481
        },
        "0.9": {
          "n": 897,
          "correct": 831,
          "answered": 897,
          "wrong_valid": 66,
          "failed": 0,
          "accuracy": 0.9264214046822743,
          "accuracy_among_usable": 0.9264214046822743
        },
        "0.95": {
          "n": 842,
          "correct": 796,
          "answered": 842,
          "wrong_valid": 46,
          "failed": 0,
          "accuracy": 0.9453681710213777,
          "accuracy_among_usable": 0.9453681710213777
        }
      },
      "latency_first_usable": {
        "n": 1342,
        "median_ms": 238.4314374648966,
        "p95_ms": 388.3725829655305
      },
      "provider_failures": 0,
      "dates_toronto": {
        "2026-10-18": 1136,
        "2026-10-19": 206
      },
      "returned_identities": {
        "inception/mercury-decide-20260930": 1342
      },
      "providers": {
        "Inception": 1342
      },
      "model_id": "mercury_decide",
      "label": "Mercury Decide",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8837209302325582,
          "accuracy_among_usable": 0.8837209302325582
        },
        "F02": {
          "n": 46,
          "correct": 43,
          "answered": 46,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9347826086956522,
          "accuracy_among_usable": 0.9347826086956522
        },
        "F03": {
          "n": 52,
          "correct": 28,
          "answered": 52,
          "wrong_valid": 24,
          "failed": 0,
          "accuracy": 0.5384615384615384,
          "accuracy_among_usable": 0.5384615384615384
        },
        "F04": {
          "n": 54,
          "correct": 49,
          "answered": 54,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.9074074074074074,
          "accuracy_among_usable": 0.9074074074074074
        },
        "F05": {
          "n": 49,
          "correct": 46,
          "answered": 49,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9387755102040817,
          "accuracy_among_usable": 0.9387755102040817
        },
        "F06": {
          "n": 40,
          "correct": 37,
          "answered": 40,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.925,
          "accuracy_among_usable": 0.925
        },
        "F07": {
          "n": 76,
          "correct": 50,
          "answered": 76,
          "wrong_valid": 26,
          "failed": 0,
          "accuracy": 0.6578947368421053,
          "accuracy_among_usable": 0.6578947368421053
        },
        "F08": {
          "n": 67,
          "correct": 52,
          "answered": 67,
          "wrong_valid": 15,
          "failed": 0,
          "accuracy": 0.7761194029850746,
          "accuracy_among_usable": 0.7761194029850746
        },
        "F09": {
          "n": 71,
          "correct": 37,
          "answered": 71,
          "wrong_valid": 34,
          "failed": 0,
          "accuracy": 0.5211267605633803,
          "accuracy_among_usable": 0.5211267605633803
        },
        "F10": {
          "n": 74,
          "correct": 39,
          "answered": 74,
          "wrong_valid": 35,
          "failed": 0,
          "accuracy": 0.527027027027027,
          "accuracy_among_usable": 0.527027027027027
        },
        "F11": {
          "n": 41,
          "correct": 30,
          "answered": 41,
          "wrong_valid": 11,
          "failed": 0,
          "accuracy": 0.7317073170731707,
          "accuracy_among_usable": 0.7317073170731707
        },
        "F12": {
          "n": 52,
          "correct": 34,
          "answered": 52,
          "wrong_valid": 18,
          "failed": 0,
          "accuracy": 0.6538461538461539,
          "accuracy_among_usable": 0.6538461538461539
        },
        "F13": {
          "n": 48,
          "correct": 12,
          "answered": 48,
          "wrong_valid": 36,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F14": {
          "n": 42,
          "correct": 35,
          "answered": 42,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.8333333333333334,
          "accuracy_among_usable": 0.8333333333333334
        },
        "F15": {
          "n": 49,
          "correct": 31,
          "answered": 49,
          "wrong_valid": 18,
          "failed": 0,
          "accuracy": 0.6326530612244898,
          "accuracy_among_usable": 0.6326530612244898
        },
        "F16": {
          "n": 50,
          "correct": 35,
          "answered": 50,
          "wrong_valid": 15,
          "failed": 0,
          "accuracy": 0.7,
          "accuracy_among_usable": 0.7
        },
        "F17": {
          "n": 50,
          "correct": 43,
          "answered": 50,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.86,
          "accuracy_among_usable": 0.86
        },
        "F18": {
          "n": 50,
          "correct": 35,
          "answered": 50,
          "wrong_valid": 15,
          "failed": 0,
          "accuracy": 0.7,
          "accuracy_among_usable": 0.7
        },
        "F19": {
          "n": 58,
          "correct": 55,
          "answered": 58,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9482758620689655,
          "accuracy_among_usable": 0.9482758620689655
        },
        "F20": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8837209302325582,
          "accuracy_among_usable": 0.8837209302325582
        },
        "F21": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9302325581395349,
          "accuracy_among_usable": 0.9302325581395349
        },
        "F22": {
          "n": 51,
          "correct": 47,
          "answered": 51,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9215686274509803,
          "accuracy_among_usable": 0.9215686274509803
        },
        "F23": {
          "n": 52,
          "correct": 51,
          "answered": 52,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9807692307692307,
          "accuracy_among_usable": 0.9807692307692307
        },
        "F24": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9302325581395349,
          "accuracy_among_usable": 0.9302325581395349
        },
        "F25": {
          "n": 50,
          "correct": 46,
          "answered": 50,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.92,
          "accuracy_among_usable": 0.92
        },
        "F26": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F27": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F28": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F29": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F30": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F31": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        }
      },
      "macro_family_accuracy": 0.7334405017644122,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 1008,
        "answered": 1305,
        "wrong_valid": 297,
        "failed": 0,
        "accuracy": 0.7724137931034483,
        "accuracy_among_usable": 0.7724137931034483
      },
      "new_domains": {
        "n": 48,
        "correct": 26,
        "answered": 48,
        "wrong_valid": 22,
        "failed": 0,
        "accuracy": 0.5416666666666666,
        "accuracy_among_usable": 0.5416666666666666
      }
    },
    "jev113": {
      "n": 1342,
      "correct": 1026,
      "answered": 1342,
      "wrong_valid": 316,
      "failed": 0,
      "accuracy": 0.7645305514157973,
      "accuracy_among_usable": 0.7645305514157973,
      "eventual": {
        "n": 1342,
        "correct": 1026,
        "answered": 1342,
        "wrong_valid": 316,
        "failed": 0,
        "accuracy": 0.7645305514157973,
        "accuracy_among_usable": 0.7645305514157973
      },
      "median_ms": 189.37308349995874,
      "p95_ms": 322.841158945812,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "model_output_failures": 0,
      "probability_warnings": 11,
      "cost": {
        "known_usd": 0.03297441,
        "known_decimal": "0.032974410",
        "unknown_attempts": 0,
        "exact_usd": 0.03297441,
        "cost_sources": {
          "recorded_accounted_or_reported": 1134,
          "api_reported": 208
        },
        "known_usd_per_1000": 0.024571095380029807
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 719,
          "correct": 702,
          "answered": 719,
          "wrong_valid": 17,
          "failed": 0,
          "accuracy": 0.9763560500695411,
          "accuracy_among_usable": 0.9763560500695411
        },
        "0.9": {
          "n": 633,
          "correct": 629,
          "answered": 633,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9936808846761453,
          "accuracy_among_usable": 0.9936808846761453
        },
        "0.95": {
          "n": 562,
          "correct": 561,
          "answered": 562,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.998220640569395,
          "accuracy_among_usable": 0.998220640569395
        }
      },
      "latency_first_usable": {
        "n": 1342,
        "median_ms": 189.37308349995874,
        "p95_ms": 322.841158945812
      },
      "provider_failures": 0,
      "dates_toronto": {
        "2026-10-15": 1134,
        "2026-10-18": 2,
        "2026-10-19": 206
      },
      "returned_identities": {
        "typesafe/jev-1.13-20260917": 1342
      },
      "providers": {
        "TypeSafe": 1342
      },
      "model_id": "jev113",
      "label": "Jev 1.13",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 41,
          "answered": 43,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.9534883720930233,
          "accuracy_among_usable": 0.9534883720930233
        },
        "F02": {
          "n": 46,
          "correct": 45,
          "answered": 46,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9782608695652174,
          "accuracy_among_usable": 0.9782608695652174
        },
        "F03": {
          "n": 52,
          "correct": 49,
          "answered": 52,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9423076923076923,
          "accuracy_among_usable": 0.9423076923076923
        },
        "F04": {
          "n": 54,
          "correct": 51,
          "answered": 54,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9444444444444444,
          "accuracy_among_usable": 0.9444444444444444
        },
        "F05": {
          "n": 49,
          "correct": 44,
          "answered": 49,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8979591836734694,
          "accuracy_among_usable": 0.8979591836734694
        },
        "F06": {
          "n": 40,
          "correct": 40,
          "answered": 40,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        },
        "F07": {
          "n": 76,
          "correct": 50,
          "answered": 76,
          "wrong_valid": 26,
          "failed": 0,
          "accuracy": 0.6578947368421053,
          "accuracy_among_usable": 0.6578947368421053
        },
        "F08": {
          "n": 67,
          "correct": 54,
          "answered": 67,
          "wrong_valid": 13,
          "failed": 0,
          "accuracy": 0.8059701492537313,
          "accuracy_among_usable": 0.8059701492537313
        },
        "F09": {
          "n": 71,
          "correct": 25,
          "answered": 71,
          "wrong_valid": 46,
          "failed": 0,
          "accuracy": 0.352112676056338,
          "accuracy_among_usable": 0.352112676056338
        },
        "F10": {
          "n": 74,
          "correct": 38,
          "answered": 74,
          "wrong_valid": 36,
          "failed": 0,
          "accuracy": 0.5135135135135135,
          "accuracy_among_usable": 0.5135135135135135
        },
        "F11": {
          "n": 41,
          "correct": 29,
          "answered": 41,
          "wrong_valid": 12,
          "failed": 0,
          "accuracy": 0.7073170731707317,
          "accuracy_among_usable": 0.7073170731707317
        },
        "F12": {
          "n": 52,
          "correct": 29,
          "answered": 52,
          "wrong_valid": 23,
          "failed": 0,
          "accuracy": 0.5576923076923077,
          "accuracy_among_usable": 0.5576923076923077
        },
        "F13": {
          "n": 48,
          "correct": 10,
          "answered": 48,
          "wrong_valid": 38,
          "failed": 0,
          "accuracy": 0.20833333333333334,
          "accuracy_among_usable": 0.20833333333333334
        },
        "F14": {
          "n": 42,
          "correct": 41,
          "answered": 42,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9761904761904762,
          "accuracy_among_usable": 0.9761904761904762
        },
        "F15": {
          "n": 49,
          "correct": 30,
          "answered": 49,
          "wrong_valid": 19,
          "failed": 0,
          "accuracy": 0.6122448979591837,
          "accuracy_among_usable": 0.6122448979591837
        },
        "F16": {
          "n": 50,
          "correct": 33,
          "answered": 50,
          "wrong_valid": 17,
          "failed": 0,
          "accuracy": 0.66,
          "accuracy_among_usable": 0.66
        },
        "F17": {
          "n": 50,
          "correct": 47,
          "answered": 50,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.94,
          "accuracy_among_usable": 0.94
        },
        "F18": {
          "n": 50,
          "correct": 42,
          "answered": 50,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.84,
          "accuracy_among_usable": 0.84
        },
        "F19": {
          "n": 58,
          "correct": 51,
          "answered": 58,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.8793103448275862,
          "accuracy_among_usable": 0.8793103448275862
        },
        "F20": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8837209302325582,
          "accuracy_among_usable": 0.8837209302325582
        },
        "F21": {
          "n": 43,
          "correct": 41,
          "answered": 43,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.9534883720930233,
          "accuracy_among_usable": 0.9534883720930233
        },
        "F22": {
          "n": 51,
          "correct": 46,
          "answered": 51,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.9019607843137255,
          "accuracy_among_usable": 0.9019607843137255
        },
        "F23": {
          "n": 52,
          "correct": 48,
          "answered": 52,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9230769230769231,
          "accuracy_among_usable": 0.9230769230769231
        },
        "F24": {
          "n": 43,
          "correct": 39,
          "answered": 43,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9069767441860465,
          "accuracy_among_usable": 0.9069767441860465
        },
        "F25": {
          "n": 50,
          "correct": 44,
          "answered": 50,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.88,
          "accuracy_among_usable": 0.88
        },
        "F26": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F27": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F28": {
          "n": 8,
          "correct": 2,
          "answered": 8,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F29": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F30": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F31": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        }
      },
      "macro_family_accuracy": 0.7258472201556591,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 1009,
        "answered": 1305,
        "wrong_valid": 296,
        "failed": 0,
        "accuracy": 0.7731800766283525,
        "accuracy_among_usable": 0.7731800766283525
      },
      "new_domains": {
        "n": 48,
        "correct": 21,
        "answered": 48,
        "wrong_valid": 27,
        "failed": 0,
        "accuracy": 0.4375,
        "accuracy_among_usable": 0.4375
      }
    },
    "luna_decisions": {
      "n": 1342,
      "correct": 758,
      "answered": 1300,
      "wrong_valid": 542,
      "failed": 42,
      "accuracy": 0.5648286140089419,
      "accuracy_among_usable": 0.583076923076923,
      "eventual": {
        "n": 1342,
        "correct": 761,
        "answered": 1306,
        "wrong_valid": 545,
        "failed": 36,
        "accuracy": 0.5670640834575261,
        "accuracy_among_usable": 0.5826952526799387
      },
      "median_ms": 253.59799998113886,
      "p95_ms": 527.3192601103807,
      "attempts": 1384,
      "recoveries": 42,
      "first_statuses": {
        "ok": 1300,
        "provider_failure": 42
      },
      "model_output_failures": 0,
      "probability_warnings": 0,
      "cost": {
        "known_usd": 0.0480967,
        "known_decimal": "0.0480967",
        "unknown_attempts": 78,
        "exact_usd": null,
        "cost_sources": {
          "recorded_accounted_or_reported": 1106,
          "unreported": 78,
          "api_reported": 200
        },
        "known_usd_per_1000": 0.03583956780923994
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 222,
          "correct": 218,
          "answered": 222,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9819819819819819,
          "accuracy_among_usable": 0.9819819819819819
        },
        "0.9": {
          "n": 144,
          "correct": 144,
          "answered": 144,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        },
        "0.95": {
          "n": 90,
          "correct": 90,
          "answered": 90,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        }
      },
      "latency_first_usable": {
        "n": 1300,
        "median_ms": 253.08333351858892,
        "p95_ms": 495.9701889660206
      },
      "provider_failures": 42,
      "dates_toronto": {
        "2026-10-15": 1134,
        "2026-10-18": 2,
        "2026-10-19": 206
      },
      "returned_identities": {
        "openai/gpt-6-luna-decisions-20261006": 1300,
        "unreported (error)": 42
      },
      "providers": {
        "OpenAI": 1300,
        "unreported": 42
      },
      "model_id": "luna_decisions",
      "label": "Luna 6 Decisions",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 39,
          "answered": 42,
          "wrong_valid": 3,
          "failed": 1,
          "accuracy": 0.9069767441860465,
          "accuracy_among_usable": 0.9285714285714286
        },
        "F02": {
          "n": 46,
          "correct": 27,
          "answered": 42,
          "wrong_valid": 15,
          "failed": 4,
          "accuracy": 0.5869565217391305,
          "accuracy_among_usable": 0.6428571428571429
        },
        "F03": {
          "n": 52,
          "correct": 15,
          "answered": 52,
          "wrong_valid": 37,
          "failed": 0,
          "accuracy": 0.28846153846153844,
          "accuracy_among_usable": 0.28846153846153844
        },
        "F04": {
          "n": 54,
          "correct": 34,
          "answered": 53,
          "wrong_valid": 19,
          "failed": 1,
          "accuracy": 0.6296296296296297,
          "accuracy_among_usable": 0.6415094339622641
        },
        "F05": {
          "n": 49,
          "correct": 38,
          "answered": 48,
          "wrong_valid": 10,
          "failed": 1,
          "accuracy": 0.7755102040816326,
          "accuracy_among_usable": 0.7916666666666666
        },
        "F06": {
          "n": 40,
          "correct": 35,
          "answered": 39,
          "wrong_valid": 4,
          "failed": 1,
          "accuracy": 0.875,
          "accuracy_among_usable": 0.8974358974358975
        },
        "F07": {
          "n": 76,
          "correct": 28,
          "answered": 73,
          "wrong_valid": 45,
          "failed": 3,
          "accuracy": 0.3684210526315789,
          "accuracy_among_usable": 0.3835616438356164
        },
        "F08": {
          "n": 67,
          "correct": 36,
          "answered": 54,
          "wrong_valid": 18,
          "failed": 13,
          "accuracy": 0.5373134328358209,
          "accuracy_among_usable": 0.6666666666666666
        },
        "F09": {
          "n": 71,
          "correct": 19,
          "answered": 70,
          "wrong_valid": 51,
          "failed": 1,
          "accuracy": 0.2676056338028169,
          "accuracy_among_usable": 0.2714285714285714
        },
        "F10": {
          "n": 74,
          "correct": 23,
          "answered": 72,
          "wrong_valid": 49,
          "failed": 2,
          "accuracy": 0.3108108108108108,
          "accuracy_among_usable": 0.3194444444444444
        },
        "F11": {
          "n": 41,
          "correct": 22,
          "answered": 41,
          "wrong_valid": 19,
          "failed": 0,
          "accuracy": 0.5365853658536586,
          "accuracy_among_usable": 0.5365853658536586
        },
        "F12": {
          "n": 52,
          "correct": 23,
          "answered": 50,
          "wrong_valid": 27,
          "failed": 2,
          "accuracy": 0.4423076923076923,
          "accuracy_among_usable": 0.46
        },
        "F13": {
          "n": 48,
          "correct": 11,
          "answered": 48,
          "wrong_valid": 37,
          "failed": 0,
          "accuracy": 0.22916666666666666,
          "accuracy_among_usable": 0.22916666666666666
        },
        "F14": {
          "n": 42,
          "correct": 25,
          "answered": 41,
          "wrong_valid": 16,
          "failed": 1,
          "accuracy": 0.5952380952380952,
          "accuracy_among_usable": 0.6097560975609756
        },
        "F15": {
          "n": 49,
          "correct": 22,
          "answered": 45,
          "wrong_valid": 23,
          "failed": 4,
          "accuracy": 0.4489795918367347,
          "accuracy_among_usable": 0.4888888888888889
        },
        "F16": {
          "n": 50,
          "correct": 17,
          "answered": 50,
          "wrong_valid": 33,
          "failed": 0,
          "accuracy": 0.34,
          "accuracy_among_usable": 0.34
        },
        "F17": {
          "n": 50,
          "correct": 32,
          "answered": 48,
          "wrong_valid": 16,
          "failed": 2,
          "accuracy": 0.64,
          "accuracy_among_usable": 0.6666666666666666
        },
        "F18": {
          "n": 50,
          "correct": 21,
          "answered": 48,
          "wrong_valid": 27,
          "failed": 2,
          "accuracy": 0.42,
          "accuracy_among_usable": 0.4375
        },
        "F19": {
          "n": 58,
          "correct": 47,
          "answered": 57,
          "wrong_valid": 10,
          "failed": 1,
          "accuracy": 0.8103448275862069,
          "accuracy_among_usable": 0.8245614035087719
        },
        "F20": {
          "n": 43,
          "correct": 25,
          "answered": 42,
          "wrong_valid": 17,
          "failed": 1,
          "accuracy": 0.5813953488372093,
          "accuracy_among_usable": 0.5952380952380952
        },
        "F21": {
          "n": 43,
          "correct": 39,
          "answered": 42,
          "wrong_valid": 3,
          "failed": 1,
          "accuracy": 0.9069767441860465,
          "accuracy_among_usable": 0.9285714285714286
        },
        "F22": {
          "n": 51,
          "correct": 44,
          "answered": 51,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.8627450980392157,
          "accuracy_among_usable": 0.8627450980392157
        },
        "F23": {
          "n": 52,
          "correct": 44,
          "answered": 51,
          "wrong_valid": 7,
          "failed": 1,
          "accuracy": 0.8461538461538461,
          "accuracy_among_usable": 0.8627450980392157
        },
        "F24": {
          "n": 43,
          "correct": 36,
          "answered": 43,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.8372093023255814,
          "accuracy_among_usable": 0.8372093023255814
        },
        "F25": {
          "n": 50,
          "correct": 34,
          "answered": 50,
          "wrong_valid": 16,
          "failed": 0,
          "accuracy": 0.68,
          "accuracy_among_usable": 0.68
        },
        "F26": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F27": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F28": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F29": {
          "n": 8,
          "correct": 2,
          "answered": 8,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F30": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F31": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        }
      },
      "macro_family_accuracy": 0.5636705853938696,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 749,
        "answered": 1267,
        "wrong_valid": 518,
        "failed": 38,
        "accuracy": 0.5739463601532567,
        "accuracy_among_usable": 0.5911602209944752
      },
      "new_domains": {
        "n": 48,
        "correct": 22,
        "answered": 48,
        "wrong_valid": 26,
        "failed": 0,
        "accuracy": 0.4583333333333333,
        "accuracy_among_usable": 0.4583333333333333
      }
    },
    "microsoft_decision": {
      "n": 1342,
      "correct": 921,
      "answered": 1342,
      "wrong_valid": 421,
      "failed": 0,
      "accuracy": 0.6862891207153502,
      "accuracy_among_usable": 0.6862891207153502,
      "eventual": {
        "n": 1342,
        "correct": 921,
        "answered": 1342,
        "wrong_valid": 421,
        "failed": 0,
        "accuracy": 0.6862891207153502,
        "accuracy_among_usable": 0.6862891207153502
      },
      "median_ms": 283.31577096832916,
      "p95_ms": 565.7315687392838,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "model_output_failures": 0,
      "probability_warnings": 0,
      "cost": {
        "known_usd": 0.016421832,
        "known_decimal": "0.016421832",
        "unknown_attempts": 0,
        "exact_usd": 0.016421832,
        "cost_sources": {
          "api_reported": 1342
        },
        "known_usd_per_1000": 0.012236834575260806
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 715,
          "correct": 654,
          "answered": 715,
          "wrong_valid": 61,
          "failed": 0,
          "accuracy": 0.9146853146853147,
          "accuracy_among_usable": 0.9146853146853147
        },
        "0.9": {
          "n": 529,
          "correct": 512,
          "answered": 529,
          "wrong_valid": 17,
          "failed": 0,
          "accuracy": 0.9678638941398866,
          "accuracy_among_usable": 0.9678638941398866
        },
        "0.95": {
          "n": 389,
          "correct": 389,
          "answered": 389,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        }
      },
      "latency_first_usable": {
        "n": 1342,
        "median_ms": 283.31577096832916,
        "p95_ms": 565.7315687392838
      },
      "provider_failures": 0,
      "dates_toronto": {
        "2026-10-16": 1134,
        "2026-10-18": 2,
        "2026-10-19": 206
      },
      "returned_identities": {
        "microsoft/microsoft-decision-1-20261009": 1342
      },
      "providers": {
        "Azure": 1342
      },
      "model_id": "microsoft_decision",
      "label": "Microsoft-Decision-1",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8837209302325582,
          "accuracy_among_usable": 0.8837209302325582
        },
        "F02": {
          "n": 46,
          "correct": 38,
          "answered": 46,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.8260869565217391,
          "accuracy_among_usable": 0.8260869565217391
        },
        "F03": {
          "n": 52,
          "correct": 25,
          "answered": 52,
          "wrong_valid": 27,
          "failed": 0,
          "accuracy": 0.4807692307692308,
          "accuracy_among_usable": 0.4807692307692308
        },
        "F04": {
          "n": 54,
          "correct": 37,
          "answered": 54,
          "wrong_valid": 17,
          "failed": 0,
          "accuracy": 0.6851851851851852,
          "accuracy_among_usable": 0.6851851851851852
        },
        "F05": {
          "n": 49,
          "correct": 41,
          "answered": 49,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.8367346938775511,
          "accuracy_among_usable": 0.8367346938775511
        },
        "F06": {
          "n": 40,
          "correct": 39,
          "answered": 40,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.975,
          "accuracy_among_usable": 0.975
        },
        "F07": {
          "n": 76,
          "correct": 41,
          "answered": 76,
          "wrong_valid": 35,
          "failed": 0,
          "accuracy": 0.5394736842105263,
          "accuracy_among_usable": 0.5394736842105263
        },
        "F08": {
          "n": 67,
          "correct": 44,
          "answered": 67,
          "wrong_valid": 23,
          "failed": 0,
          "accuracy": 0.6567164179104478,
          "accuracy_among_usable": 0.6567164179104478
        },
        "F09": {
          "n": 71,
          "correct": 40,
          "answered": 71,
          "wrong_valid": 31,
          "failed": 0,
          "accuracy": 0.5633802816901409,
          "accuracy_among_usable": 0.5633802816901409
        },
        "F10": {
          "n": 74,
          "correct": 36,
          "answered": 74,
          "wrong_valid": 38,
          "failed": 0,
          "accuracy": 0.4864864864864865,
          "accuracy_among_usable": 0.4864864864864865
        },
        "F11": {
          "n": 41,
          "correct": 28,
          "answered": 41,
          "wrong_valid": 13,
          "failed": 0,
          "accuracy": 0.6829268292682927,
          "accuracy_among_usable": 0.6829268292682927
        },
        "F12": {
          "n": 52,
          "correct": 24,
          "answered": 52,
          "wrong_valid": 28,
          "failed": 0,
          "accuracy": 0.46153846153846156,
          "accuracy_among_usable": 0.46153846153846156
        },
        "F13": {
          "n": 48,
          "correct": 7,
          "answered": 48,
          "wrong_valid": 41,
          "failed": 0,
          "accuracy": 0.14583333333333334,
          "accuracy_among_usable": 0.14583333333333334
        },
        "F14": {
          "n": 42,
          "correct": 33,
          "answered": 42,
          "wrong_valid": 9,
          "failed": 0,
          "accuracy": 0.7857142857142857,
          "accuracy_among_usable": 0.7857142857142857
        },
        "F15": {
          "n": 49,
          "correct": 24,
          "answered": 49,
          "wrong_valid": 25,
          "failed": 0,
          "accuracy": 0.4897959183673469,
          "accuracy_among_usable": 0.4897959183673469
        },
        "F16": {
          "n": 50,
          "correct": 32,
          "answered": 50,
          "wrong_valid": 18,
          "failed": 0,
          "accuracy": 0.64,
          "accuracy_among_usable": 0.64
        },
        "F17": {
          "n": 50,
          "correct": 42,
          "answered": 50,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.84,
          "accuracy_among_usable": 0.84
        },
        "F18": {
          "n": 50,
          "correct": 24,
          "answered": 50,
          "wrong_valid": 26,
          "failed": 0,
          "accuracy": 0.48,
          "accuracy_among_usable": 0.48
        },
        "F19": {
          "n": 58,
          "correct": 52,
          "answered": 58,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.896551724137931,
          "accuracy_among_usable": 0.896551724137931
        },
        "F20": {
          "n": 43,
          "correct": 37,
          "answered": 43,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.8604651162790697,
          "accuracy_among_usable": 0.8604651162790697
        },
        "F21": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9302325581395349,
          "accuracy_among_usable": 0.9302325581395349
        },
        "F22": {
          "n": 51,
          "correct": 44,
          "answered": 51,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.8627450980392157,
          "accuracy_among_usable": 0.8627450980392157
        },
        "F23": {
          "n": 52,
          "correct": 47,
          "answered": 52,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.9038461538461539,
          "accuracy_among_usable": 0.9038461538461539
        },
        "F24": {
          "n": 43,
          "correct": 39,
          "answered": 43,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9069767441860465,
          "accuracy_among_usable": 0.9069767441860465
        },
        "F25": {
          "n": 50,
          "correct": 46,
          "answered": 50,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.92,
          "accuracy_among_usable": 0.92
        },
        "F26": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F27": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F28": {
          "n": 8,
          "correct": 2,
          "answered": 8,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F29": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F30": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F31": {
          "n": 8,
          "correct": 6,
          "answered": 8,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.75,
          "accuracy_among_usable": 0.75
        }
      },
      "macro_family_accuracy": 0.6650058093462433,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 909,
        "answered": 1305,
        "wrong_valid": 396,
        "failed": 0,
        "accuracy": 0.696551724137931,
        "accuracy_among_usable": 0.696551724137931
      },
      "new_domains": {
        "n": 48,
        "correct": 23,
        "answered": 48,
        "wrong_valid": 25,
        "failed": 0,
        "accuracy": 0.4791666666666667,
        "accuracy_among_usable": 0.4791666666666667
      }
    },
    "liquid_d1": {
      "n": 1342,
      "correct": 965,
      "answered": 1342,
      "wrong_valid": 377,
      "failed": 0,
      "accuracy": 0.7190760059612519,
      "accuracy_among_usable": 0.7190760059612519,
      "eventual": {
        "n": 1342,
        "correct": 965,
        "answered": 1342,
        "wrong_valid": 377,
        "failed": 0,
        "accuracy": 0.7190760059612519,
        "accuracy_among_usable": 0.7190760059612519
      },
      "median_ms": 206.22245804406703,
      "p95_ms": 826.7250909528241,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "model_output_failures": 0,
      "probability_warnings": 0,
      "cost": {
        "known_usd": 0.00774762,
        "known_decimal": "0.00774762",
        "unknown_attempts": 0,
        "exact_usd": 0.00774762,
        "cost_sources": {
          "api_reported": 1342
        },
        "known_usd_per_1000": 0.005773189269746647
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 701,
          "correct": 674,
          "answered": 701,
          "wrong_valid": 27,
          "failed": 0,
          "accuracy": 0.9614835948644793,
          "accuracy_among_usable": 0.9614835948644793
        },
        "0.9": {
          "n": 617,
          "correct": 610,
          "answered": 617,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.9886547811993517,
          "accuracy_among_usable": 0.9886547811993517
        },
        "0.95": {
          "n": 567,
          "correct": 565,
          "answered": 567,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.9964726631393298,
          "accuracy_among_usable": 0.9964726631393298
        }
      },
      "latency_first_usable": {
        "n": 1342,
        "median_ms": 206.22245804406703,
        "p95_ms": 826.7250909528241
      },
      "provider_failures": 0,
      "dates_toronto": {
        "2026-10-18": 1136,
        "2026-10-19": 206
      },
      "returned_identities": {
        "liquid/d1-20260930": 1342
      },
      "providers": {
        "Liquid": 1342
      },
      "model_id": "liquid_d1",
      "label": "Liquid d1",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9302325581395349,
          "accuracy_among_usable": 0.9302325581395349
        },
        "F02": {
          "n": 46,
          "correct": 41,
          "answered": 46,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8913043478260869,
          "accuracy_among_usable": 0.8913043478260869
        },
        "F03": {
          "n": 52,
          "correct": 35,
          "answered": 52,
          "wrong_valid": 17,
          "failed": 0,
          "accuracy": 0.6730769230769231,
          "accuracy_among_usable": 0.6730769230769231
        },
        "F04": {
          "n": 54,
          "correct": 50,
          "answered": 54,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9259259259259259,
          "accuracy_among_usable": 0.9259259259259259
        },
        "F05": {
          "n": 49,
          "correct": 42,
          "answered": 49,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.8571428571428571,
          "accuracy_among_usable": 0.8571428571428571
        },
        "F06": {
          "n": 40,
          "correct": 38,
          "answered": 40,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.95,
          "accuracy_among_usable": 0.95
        },
        "F07": {
          "n": 76,
          "correct": 47,
          "answered": 76,
          "wrong_valid": 29,
          "failed": 0,
          "accuracy": 0.618421052631579,
          "accuracy_among_usable": 0.618421052631579
        },
        "F08": {
          "n": 67,
          "correct": 48,
          "answered": 67,
          "wrong_valid": 19,
          "failed": 0,
          "accuracy": 0.7164179104477612,
          "accuracy_among_usable": 0.7164179104477612
        },
        "F09": {
          "n": 71,
          "correct": 23,
          "answered": 71,
          "wrong_valid": 48,
          "failed": 0,
          "accuracy": 0.323943661971831,
          "accuracy_among_usable": 0.323943661971831
        },
        "F10": {
          "n": 74,
          "correct": 40,
          "answered": 74,
          "wrong_valid": 34,
          "failed": 0,
          "accuracy": 0.5405405405405406,
          "accuracy_among_usable": 0.5405405405405406
        },
        "F11": {
          "n": 41,
          "correct": 32,
          "answered": 41,
          "wrong_valid": 9,
          "failed": 0,
          "accuracy": 0.7804878048780488,
          "accuracy_among_usable": 0.7804878048780488
        },
        "F12": {
          "n": 52,
          "correct": 33,
          "answered": 52,
          "wrong_valid": 19,
          "failed": 0,
          "accuracy": 0.6346153846153846,
          "accuracy_among_usable": 0.6346153846153846
        },
        "F13": {
          "n": 48,
          "correct": 9,
          "answered": 48,
          "wrong_valid": 39,
          "failed": 0,
          "accuracy": 0.1875,
          "accuracy_among_usable": 0.1875
        },
        "F14": {
          "n": 42,
          "correct": 37,
          "answered": 42,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8809523809523809,
          "accuracy_among_usable": 0.8809523809523809
        },
        "F15": {
          "n": 49,
          "correct": 24,
          "answered": 49,
          "wrong_valid": 25,
          "failed": 0,
          "accuracy": 0.4897959183673469,
          "accuracy_among_usable": 0.4897959183673469
        },
        "F16": {
          "n": 50,
          "correct": 29,
          "answered": 50,
          "wrong_valid": 21,
          "failed": 0,
          "accuracy": 0.58,
          "accuracy_among_usable": 0.58
        },
        "F17": {
          "n": 50,
          "correct": 41,
          "answered": 50,
          "wrong_valid": 9,
          "failed": 0,
          "accuracy": 0.82,
          "accuracy_among_usable": 0.82
        },
        "F18": {
          "n": 50,
          "correct": 28,
          "answered": 50,
          "wrong_valid": 22,
          "failed": 0,
          "accuracy": 0.56,
          "accuracy_among_usable": 0.56
        },
        "F19": {
          "n": 58,
          "correct": 51,
          "answered": 58,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.8793103448275862,
          "accuracy_among_usable": 0.8793103448275862
        },
        "F20": {
          "n": 43,
          "correct": 39,
          "answered": 43,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9069767441860465,
          "accuracy_among_usable": 0.9069767441860465
        },
        "F21": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9302325581395349,
          "accuracy_among_usable": 0.9302325581395349
        },
        "F22": {
          "n": 51,
          "correct": 46,
          "answered": 51,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.9019607843137255,
          "accuracy_among_usable": 0.9019607843137255
        },
        "F23": {
          "n": 52,
          "correct": 49,
          "answered": 52,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9423076923076923,
          "accuracy_among_usable": 0.9423076923076923
        },
        "F24": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8837209302325582,
          "accuracy_among_usable": 0.8837209302325582
        },
        "F25": {
          "n": 50,
          "correct": 46,
          "answered": 50,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.92,
          "accuracy_among_usable": 0.92
        },
        "F26": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F27": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F28": {
          "n": 8,
          "correct": 2,
          "answered": 8,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F29": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F30": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F31": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        }
      },
      "macro_family_accuracy": 0.6806408490491404,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 948,
        "answered": 1305,
        "wrong_valid": 357,
        "failed": 0,
        "accuracy": 0.7264367816091954,
        "accuracy_among_usable": 0.7264367816091954
      },
      "new_domains": {
        "n": 48,
        "correct": 19,
        "answered": 48,
        "wrong_valid": 29,
        "failed": 0,
        "accuracy": 0.3958333333333333,
        "accuracy_among_usable": 0.3958333333333333
      }
    },
    "pplx_flash12": {
      "n": 1342,
      "correct": 923,
      "answered": 1286,
      "wrong_valid": 363,
      "failed": 56,
      "accuracy": 0.687779433681073,
      "accuracy_among_usable": 0.7177293934681181,
      "eventual": {
        "n": 1342,
        "correct": 940,
        "answered": 1308,
        "wrong_valid": 368,
        "failed": 34,
        "accuracy": 0.7004470938897168,
        "accuracy_among_usable": 0.7186544342507645
      },
      "median_ms": 158.6297499598004,
      "p95_ms": 230.8821223326959,
      "attempts": 1398,
      "recoveries": 56,
      "first_statuses": {
        "ok": 1286,
        "provider_failure": 56
      },
      "model_output_failures": 0,
      "probability_warnings": 0,
      "cost": {
        "known_usd": 0.00457042,
        "known_decimal": "0.00457042",
        "unknown_attempts": 90,
        "exact_usd": null,
        "cost_sources": {
          "api_reported": 1308,
          "unreported": 90
        },
        "known_usd_per_1000": 0.003405678092399404
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 808,
          "correct": 748,
          "answered": 808,
          "wrong_valid": 60,
          "failed": 0,
          "accuracy": 0.9257425742574258,
          "accuracy_among_usable": 0.9257425742574258
        },
        "0.9": {
          "n": 713,
          "correct": 674,
          "answered": 713,
          "wrong_valid": 39,
          "failed": 0,
          "accuracy": 0.9453015427769986,
          "accuracy_among_usable": 0.9453015427769986
        },
        "0.95": {
          "n": 648,
          "correct": 629,
          "answered": 648,
          "wrong_valid": 19,
          "failed": 0,
          "accuracy": 0.970679012345679,
          "accuracy_among_usable": 0.970679012345679
        }
      },
      "latency_first_usable": {
        "n": 1286,
        "median_ms": 159.40052102087066,
        "p95_ms": 232.63112452696078
      },
      "provider_failures": 56,
      "dates_toronto": {
        "2026-10-18": 1136,
        "2026-10-19": 206
      },
      "returned_identities": {
        "perplexity/pplx-decider-flash-v1.2-20261016": 1286,
        "unreported (error)": 56
      },
      "providers": {
        "Perplexity": 1286,
        "unreported": 56
      },
      "model_id": "pplx_flash12",
      "label": "Perplexity Decider Flash v1.2",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 36,
          "answered": 40,
          "wrong_valid": 4,
          "failed": 3,
          "accuracy": 0.8372093023255814,
          "accuracy_among_usable": 0.9
        },
        "F02": {
          "n": 46,
          "correct": 43,
          "answered": 46,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9347826086956522,
          "accuracy_among_usable": 0.9347826086956522
        },
        "F03": {
          "n": 52,
          "correct": 41,
          "answered": 51,
          "wrong_valid": 10,
          "failed": 1,
          "accuracy": 0.7884615384615384,
          "accuracy_among_usable": 0.803921568627451
        },
        "F04": {
          "n": 54,
          "correct": 38,
          "answered": 51,
          "wrong_valid": 13,
          "failed": 3,
          "accuracy": 0.7037037037037037,
          "accuracy_among_usable": 0.7450980392156863
        },
        "F05": {
          "n": 49,
          "correct": 38,
          "answered": 45,
          "wrong_valid": 7,
          "failed": 4,
          "accuracy": 0.7755102040816326,
          "accuracy_among_usable": 0.8444444444444444
        },
        "F06": {
          "n": 40,
          "correct": 37,
          "answered": 39,
          "wrong_valid": 2,
          "failed": 1,
          "accuracy": 0.925,
          "accuracy_among_usable": 0.9487179487179487
        },
        "F07": {
          "n": 76,
          "correct": 40,
          "answered": 73,
          "wrong_valid": 33,
          "failed": 3,
          "accuracy": 0.5263157894736842,
          "accuracy_among_usable": 0.547945205479452
        },
        "F08": {
          "n": 67,
          "correct": 47,
          "answered": 65,
          "wrong_valid": 18,
          "failed": 2,
          "accuracy": 0.7014925373134329,
          "accuracy_among_usable": 0.7230769230769231
        },
        "F09": {
          "n": 71,
          "correct": 38,
          "answered": 69,
          "wrong_valid": 31,
          "failed": 2,
          "accuracy": 0.5352112676056338,
          "accuracy_among_usable": 0.5507246376811594
        },
        "F10": {
          "n": 74,
          "correct": 30,
          "answered": 67,
          "wrong_valid": 37,
          "failed": 7,
          "accuracy": 0.40540540540540543,
          "accuracy_among_usable": 0.44776119402985076
        },
        "F11": {
          "n": 41,
          "correct": 30,
          "answered": 40,
          "wrong_valid": 10,
          "failed": 1,
          "accuracy": 0.7317073170731707,
          "accuracy_among_usable": 0.75
        },
        "F12": {
          "n": 52,
          "correct": 23,
          "answered": 50,
          "wrong_valid": 27,
          "failed": 2,
          "accuracy": 0.4423076923076923,
          "accuracy_among_usable": 0.46
        },
        "F13": {
          "n": 48,
          "correct": 12,
          "answered": 45,
          "wrong_valid": 33,
          "failed": 3,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.26666666666666666
        },
        "F14": {
          "n": 42,
          "correct": 28,
          "answered": 41,
          "wrong_valid": 13,
          "failed": 1,
          "accuracy": 0.6666666666666666,
          "accuracy_among_usable": 0.6829268292682927
        },
        "F15": {
          "n": 49,
          "correct": 25,
          "answered": 47,
          "wrong_valid": 22,
          "failed": 2,
          "accuracy": 0.5102040816326531,
          "accuracy_among_usable": 0.5319148936170213
        },
        "F16": {
          "n": 50,
          "correct": 34,
          "answered": 49,
          "wrong_valid": 15,
          "failed": 1,
          "accuracy": 0.68,
          "accuracy_among_usable": 0.6938775510204082
        },
        "F17": {
          "n": 50,
          "correct": 42,
          "answered": 48,
          "wrong_valid": 6,
          "failed": 2,
          "accuracy": 0.84,
          "accuracy_among_usable": 0.875
        },
        "F18": {
          "n": 50,
          "correct": 29,
          "answered": 47,
          "wrong_valid": 18,
          "failed": 3,
          "accuracy": 0.58,
          "accuracy_among_usable": 0.6170212765957447
        },
        "F19": {
          "n": 58,
          "correct": 47,
          "answered": 52,
          "wrong_valid": 5,
          "failed": 6,
          "accuracy": 0.8103448275862069,
          "accuracy_among_usable": 0.9038461538461539
        },
        "F20": {
          "n": 43,
          "correct": 37,
          "answered": 42,
          "wrong_valid": 5,
          "failed": 1,
          "accuracy": 0.8604651162790697,
          "accuracy_among_usable": 0.8809523809523809
        },
        "F21": {
          "n": 43,
          "correct": 40,
          "answered": 42,
          "wrong_valid": 2,
          "failed": 1,
          "accuracy": 0.9302325581395349,
          "accuracy_among_usable": 0.9523809523809523
        },
        "F22": {
          "n": 51,
          "correct": 45,
          "answered": 49,
          "wrong_valid": 4,
          "failed": 2,
          "accuracy": 0.8823529411764706,
          "accuracy_among_usable": 0.9183673469387755
        },
        "F23": {
          "n": 52,
          "correct": 47,
          "answered": 50,
          "wrong_valid": 3,
          "failed": 2,
          "accuracy": 0.9038461538461539,
          "accuracy_among_usable": 0.94
        },
        "F24": {
          "n": 43,
          "correct": 39,
          "answered": 42,
          "wrong_valid": 3,
          "failed": 1,
          "accuracy": 0.9069767441860465,
          "accuracy_among_usable": 0.9285714285714286
        },
        "F25": {
          "n": 50,
          "correct": 39,
          "answered": 48,
          "wrong_valid": 9,
          "failed": 2,
          "accuracy": 0.78,
          "accuracy_among_usable": 0.8125
        },
        "F26": {
          "n": 8,
          "correct": 2,
          "answered": 8,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F27": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F28": {
          "n": 8,
          "correct": 2,
          "answered": 8,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F29": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F30": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F31": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        }
      },
      "macro_family_accuracy": 0.650264401805159,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 915,
        "answered": 1249,
        "wrong_valid": 334,
        "failed": 56,
        "accuracy": 0.7011494252873564,
        "accuracy_among_usable": 0.732586068855084
      },
      "new_domains": {
        "n": 48,
        "correct": 18,
        "answered": 48,
        "wrong_valid": 30,
        "failed": 0,
        "accuracy": 0.375,
        "accuracy_among_usable": 0.375
      }
    },
    "clef": {
      "n": 1342,
      "correct": 936,
      "answered": 1342,
      "wrong_valid": 406,
      "failed": 0,
      "accuracy": 0.6974664679582713,
      "accuracy_among_usable": 0.6974664679582713,
      "eventual": {
        "n": 1342,
        "correct": 936,
        "answered": 1342,
        "wrong_valid": 406,
        "failed": 0,
        "accuracy": 0.6974664679582713,
        "accuracy_among_usable": 0.6974664679582713
      },
      "median_ms": 267.92083302279934,
      "p95_ms": 416.5649816102814,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "model_output_failures": 0,
      "probability_warnings": 562,
      "cost": {
        "known_usd": 0.023611182,
        "known_decimal": "0.023611182",
        "unknown_attempts": 0,
        "exact_usd": 0.023611182,
        "cost_sources": {
          "api_reported": 1342
        },
        "known_usd_per_1000": 0.017594025335320417
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 669,
          "correct": 645,
          "answered": 669,
          "wrong_valid": 24,
          "failed": 0,
          "accuracy": 0.9641255605381166,
          "accuracy_among_usable": 0.9641255605381166
        },
        "0.9": {
          "n": 566,
          "correct": 558,
          "answered": 566,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.9858657243816255,
          "accuracy_among_usable": 0.9858657243816255
        },
        "0.95": {
          "n": 455,
          "correct": 453,
          "answered": 455,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.9956043956043956,
          "accuracy_among_usable": 0.9956043956043956
        }
      },
      "latency_first_usable": {
        "n": 1342,
        "median_ms": 267.92083302279934,
        "p95_ms": 416.5649816102814
      },
      "provider_failures": 0,
      "dates_toronto": {
        "2026-10-18": 1136,
        "2026-10-19": 206
      },
      "returned_identities": {
        "cloudflare/clef": 1342
      },
      "providers": {
        "PrimeIntellect": 1342
      },
      "model_id": "clef",
      "label": "Cloudflare Clef",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9302325581395349,
          "accuracy_among_usable": 0.9302325581395349
        },
        "F02": {
          "n": 46,
          "correct": 39,
          "answered": 46,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.8478260869565217,
          "accuracy_among_usable": 0.8478260869565217
        },
        "F03": {
          "n": 52,
          "correct": 39,
          "answered": 52,
          "wrong_valid": 13,
          "failed": 0,
          "accuracy": 0.75,
          "accuracy_among_usable": 0.75
        },
        "F04": {
          "n": 54,
          "correct": 46,
          "answered": 54,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.8518518518518519,
          "accuracy_among_usable": 0.8518518518518519
        },
        "F05": {
          "n": 49,
          "correct": 44,
          "answered": 49,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8979591836734694,
          "accuracy_among_usable": 0.8979591836734694
        },
        "F06": {
          "n": 40,
          "correct": 37,
          "answered": 40,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.925,
          "accuracy_among_usable": 0.925
        },
        "F07": {
          "n": 76,
          "correct": 43,
          "answered": 76,
          "wrong_valid": 33,
          "failed": 0,
          "accuracy": 0.5657894736842105,
          "accuracy_among_usable": 0.5657894736842105
        },
        "F08": {
          "n": 67,
          "correct": 42,
          "answered": 67,
          "wrong_valid": 25,
          "failed": 0,
          "accuracy": 0.6268656716417911,
          "accuracy_among_usable": 0.6268656716417911
        },
        "F09": {
          "n": 71,
          "correct": 27,
          "answered": 71,
          "wrong_valid": 44,
          "failed": 0,
          "accuracy": 0.38028169014084506,
          "accuracy_among_usable": 0.38028169014084506
        },
        "F10": {
          "n": 74,
          "correct": 33,
          "answered": 74,
          "wrong_valid": 41,
          "failed": 0,
          "accuracy": 0.44594594594594594,
          "accuracy_among_usable": 0.44594594594594594
        },
        "F11": {
          "n": 41,
          "correct": 29,
          "answered": 41,
          "wrong_valid": 12,
          "failed": 0,
          "accuracy": 0.7073170731707317,
          "accuracy_among_usable": 0.7073170731707317
        },
        "F12": {
          "n": 52,
          "correct": 27,
          "answered": 52,
          "wrong_valid": 25,
          "failed": 0,
          "accuracy": 0.5192307692307693,
          "accuracy_among_usable": 0.5192307692307693
        },
        "F13": {
          "n": 48,
          "correct": 11,
          "answered": 48,
          "wrong_valid": 37,
          "failed": 0,
          "accuracy": 0.22916666666666666,
          "accuracy_among_usable": 0.22916666666666666
        },
        "F14": {
          "n": 42,
          "correct": 31,
          "answered": 42,
          "wrong_valid": 11,
          "failed": 0,
          "accuracy": 0.7380952380952381,
          "accuracy_among_usable": 0.7380952380952381
        },
        "F15": {
          "n": 49,
          "correct": 23,
          "answered": 49,
          "wrong_valid": 26,
          "failed": 0,
          "accuracy": 0.46938775510204084,
          "accuracy_among_usable": 0.46938775510204084
        },
        "F16": {
          "n": 50,
          "correct": 31,
          "answered": 50,
          "wrong_valid": 19,
          "failed": 0,
          "accuracy": 0.62,
          "accuracy_among_usable": 0.62
        },
        "F17": {
          "n": 50,
          "correct": 42,
          "answered": 50,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.84,
          "accuracy_among_usable": 0.84
        },
        "F18": {
          "n": 50,
          "correct": 27,
          "answered": 50,
          "wrong_valid": 23,
          "failed": 0,
          "accuracy": 0.54,
          "accuracy_among_usable": 0.54
        },
        "F19": {
          "n": 58,
          "correct": 51,
          "answered": 58,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.8793103448275862,
          "accuracy_among_usable": 0.8793103448275862
        },
        "F20": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8837209302325582,
          "accuracy_among_usable": 0.8837209302325582
        },
        "F21": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9302325581395349,
          "accuracy_among_usable": 0.9302325581395349
        },
        "F22": {
          "n": 51,
          "correct": 45,
          "answered": 51,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.8823529411764706,
          "accuracy_among_usable": 0.8823529411764706
        },
        "F23": {
          "n": 52,
          "correct": 49,
          "answered": 52,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9423076923076923,
          "accuracy_among_usable": 0.9423076923076923
        },
        "F24": {
          "n": 43,
          "correct": 39,
          "answered": 43,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9069767441860465,
          "accuracy_among_usable": 0.9069767441860465
        },
        "F25": {
          "n": 50,
          "correct": 41,
          "answered": 50,
          "wrong_valid": 9,
          "failed": 0,
          "accuracy": 0.82,
          "accuracy_among_usable": 0.82
        },
        "F26": {
          "n": 8,
          "correct": 2,
          "answered": 8,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F27": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F28": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F29": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F30": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F31": {
          "n": 8,
          "correct": 6,
          "answered": 8,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.75,
          "accuracy_among_usable": 0.75
        }
      },
      "macro_family_accuracy": 0.6735435862957904,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 926,
        "answered": 1305,
        "wrong_valid": 379,
        "failed": 0,
        "accuracy": 0.7095785440613027,
        "accuracy_among_usable": 0.7095785440613027
      },
      "new_domains": {
        "n": 48,
        "correct": 22,
        "answered": 48,
        "wrong_valid": 26,
        "failed": 0,
        "accuracy": 0.4583333333333333,
        "accuracy_among_usable": 0.4583333333333333
      }
    },
    "clef_flash": {
      "n": 1342,
      "correct": 860,
      "answered": 1342,
      "wrong_valid": 482,
      "failed": 0,
      "accuracy": 0.6408345752608048,
      "accuracy_among_usable": 0.6408345752608048,
      "eventual": {
        "n": 1342,
        "correct": 860,
        "answered": 1342,
        "wrong_valid": 482,
        "failed": 0,
        "accuracy": 0.6408345752608048,
        "accuracy_among_usable": 0.6408345752608048
      },
      "median_ms": 244.66049950569868,
      "p95_ms": 352.7314375038259,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "model_output_failures": 0,
      "probability_warnings": 555,
      "cost": {
        "known_usd": 0.011805591,
        "known_decimal": "0.011805591",
        "unknown_attempts": 0,
        "exact_usd": 0.011805591,
        "cost_sources": {
          "api_reported": 1342
        },
        "known_usd_per_1000": 0.008797012667660208
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 529,
          "correct": 498,
          "answered": 529,
          "wrong_valid": 31,
          "failed": 0,
          "accuracy": 0.941398865784499,
          "accuracy_among_usable": 0.941398865784499
        },
        "0.9": {
          "n": 344,
          "correct": 334,
          "answered": 344,
          "wrong_valid": 10,
          "failed": 0,
          "accuracy": 0.9709302325581395,
          "accuracy_among_usable": 0.9709302325581395
        },
        "0.95": {
          "n": 178,
          "correct": 177,
          "answered": 178,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9943820224719101,
          "accuracy_among_usable": 0.9943820224719101
        }
      },
      "latency_first_usable": {
        "n": 1342,
        "median_ms": 244.66049950569868,
        "p95_ms": 352.7314375038259
      },
      "provider_failures": 0,
      "dates_toronto": {
        "2026-10-18": 1136,
        "2026-10-19": 206
      },
      "returned_identities": {
        "cloudflare/clef-flash": 1342
      },
      "providers": {
        "PrimeIntellect": 1342
      },
      "model_id": "clef_flash",
      "label": "Cloudflare Clef Flash",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8837209302325582,
          "accuracy_among_usable": 0.8837209302325582
        },
        "F02": {
          "n": 46,
          "correct": 34,
          "answered": 46,
          "wrong_valid": 12,
          "failed": 0,
          "accuracy": 0.7391304347826086,
          "accuracy_among_usable": 0.7391304347826086
        },
        "F03": {
          "n": 52,
          "correct": 35,
          "answered": 52,
          "wrong_valid": 17,
          "failed": 0,
          "accuracy": 0.6730769230769231,
          "accuracy_among_usable": 0.6730769230769231
        },
        "F04": {
          "n": 54,
          "correct": 37,
          "answered": 54,
          "wrong_valid": 17,
          "failed": 0,
          "accuracy": 0.6851851851851852,
          "accuracy_among_usable": 0.6851851851851852
        },
        "F05": {
          "n": 49,
          "correct": 42,
          "answered": 49,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.8571428571428571,
          "accuracy_among_usable": 0.8571428571428571
        },
        "F06": {
          "n": 40,
          "correct": 32,
          "answered": 40,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.8,
          "accuracy_among_usable": 0.8
        },
        "F07": {
          "n": 76,
          "correct": 35,
          "answered": 76,
          "wrong_valid": 41,
          "failed": 0,
          "accuracy": 0.4605263157894737,
          "accuracy_among_usable": 0.4605263157894737
        },
        "F08": {
          "n": 67,
          "correct": 48,
          "answered": 67,
          "wrong_valid": 19,
          "failed": 0,
          "accuracy": 0.7164179104477612,
          "accuracy_among_usable": 0.7164179104477612
        },
        "F09": {
          "n": 71,
          "correct": 28,
          "answered": 71,
          "wrong_valid": 43,
          "failed": 0,
          "accuracy": 0.39436619718309857,
          "accuracy_among_usable": 0.39436619718309857
        },
        "F10": {
          "n": 74,
          "correct": 34,
          "answered": 74,
          "wrong_valid": 40,
          "failed": 0,
          "accuracy": 0.4594594594594595,
          "accuracy_among_usable": 0.4594594594594595
        },
        "F11": {
          "n": 41,
          "correct": 27,
          "answered": 41,
          "wrong_valid": 14,
          "failed": 0,
          "accuracy": 0.6585365853658537,
          "accuracy_among_usable": 0.6585365853658537
        },
        "F12": {
          "n": 52,
          "correct": 28,
          "answered": 52,
          "wrong_valid": 24,
          "failed": 0,
          "accuracy": 0.5384615384615384,
          "accuracy_among_usable": 0.5384615384615384
        },
        "F13": {
          "n": 48,
          "correct": 9,
          "answered": 48,
          "wrong_valid": 39,
          "failed": 0,
          "accuracy": 0.1875,
          "accuracy_among_usable": 0.1875
        },
        "F14": {
          "n": 42,
          "correct": 22,
          "answered": 42,
          "wrong_valid": 20,
          "failed": 0,
          "accuracy": 0.5238095238095238,
          "accuracy_among_usable": 0.5238095238095238
        },
        "F15": {
          "n": 49,
          "correct": 16,
          "answered": 49,
          "wrong_valid": 33,
          "failed": 0,
          "accuracy": 0.32653061224489793,
          "accuracy_among_usable": 0.32653061224489793
        },
        "F16": {
          "n": 50,
          "correct": 25,
          "answered": 50,
          "wrong_valid": 25,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F17": {
          "n": 50,
          "correct": 41,
          "answered": 50,
          "wrong_valid": 9,
          "failed": 0,
          "accuracy": 0.82,
          "accuracy_among_usable": 0.82
        },
        "F18": {
          "n": 50,
          "correct": 29,
          "answered": 50,
          "wrong_valid": 21,
          "failed": 0,
          "accuracy": 0.58,
          "accuracy_among_usable": 0.58
        },
        "F19": {
          "n": 58,
          "correct": 43,
          "answered": 58,
          "wrong_valid": 15,
          "failed": 0,
          "accuracy": 0.7413793103448276,
          "accuracy_among_usable": 0.7413793103448276
        },
        "F20": {
          "n": 43,
          "correct": 33,
          "answered": 43,
          "wrong_valid": 10,
          "failed": 0,
          "accuracy": 0.7674418604651163,
          "accuracy_among_usable": 0.7674418604651163
        },
        "F21": {
          "n": 43,
          "correct": 36,
          "answered": 43,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.8372093023255814,
          "accuracy_among_usable": 0.8372093023255814
        },
        "F22": {
          "n": 51,
          "correct": 45,
          "answered": 51,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.8823529411764706,
          "accuracy_among_usable": 0.8823529411764706
        },
        "F23": {
          "n": 52,
          "correct": 44,
          "answered": 52,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.8461538461538461,
          "accuracy_among_usable": 0.8461538461538461
        },
        "F24": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8837209302325582,
          "accuracy_among_usable": 0.8837209302325582
        },
        "F25": {
          "n": 50,
          "correct": 40,
          "answered": 50,
          "wrong_valid": 10,
          "failed": 0,
          "accuracy": 0.8,
          "accuracy_among_usable": 0.8
        },
        "F26": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F27": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F28": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F29": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F30": {
          "n": 8,
          "correct": 2,
          "answered": 8,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F31": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        }
      },
      "macro_family_accuracy": 0.618939440770327,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 850,
        "answered": 1305,
        "wrong_valid": 455,
        "failed": 0,
        "accuracy": 0.6513409961685823,
        "accuracy_among_usable": 0.6513409961685823
      },
      "new_domains": {
        "n": 48,
        "correct": 21,
        "answered": 48,
        "wrong_valid": 27,
        "failed": 0,
        "accuracy": 0.4375,
        "accuracy_among_usable": 0.4375
      }
    },
    "clef_omni": {
      "n": 1342,
      "correct": 860,
      "answered": 1341,
      "wrong_valid": 481,
      "failed": 1,
      "accuracy": 0.6408345752608048,
      "accuracy_among_usable": 0.6413124533929903,
      "eventual": {
        "n": 1342,
        "correct": 861,
        "answered": 1342,
        "wrong_valid": 481,
        "failed": 0,
        "accuracy": 0.6415797317436661,
        "accuracy_among_usable": 0.6415797317436661
      },
      "median_ms": 240.51106302067637,
      "p95_ms": 399.6966604376212,
      "attempts": 1343,
      "recoveries": 1,
      "first_statuses": {
        "ok": 1341,
        "provider_failure": 1
      },
      "model_output_failures": 0,
      "probability_warnings": 0,
      "cost": {
        "known_usd": 0.0825471,
        "known_decimal": "0.08254710",
        "unknown_attempts": 1,
        "exact_usd": null,
        "cost_sources": {
          "api_reported": 1342,
          "unreported": 1
        },
        "known_usd_per_1000": 0.06151050670640834
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 145,
          "correct": 132,
          "answered": 145,
          "wrong_valid": 13,
          "failed": 0,
          "accuracy": 0.9103448275862069,
          "accuracy_among_usable": 0.9103448275862069
        },
        "0.9": {
          "n": 5,
          "correct": 5,
          "answered": 5,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        },
        "0.95": {
          "n": 0,
          "correct": 0,
          "answered": 0,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": null,
          "accuracy_among_usable": null
        }
      },
      "latency_first_usable": {
        "n": 1341,
        "median_ms": 240.54758402053267,
        "p95_ms": 399.72724998369813
      },
      "provider_failures": 1,
      "dates_toronto": {
        "2026-10-18": 1136,
        "2026-10-19": 206
      },
      "returned_identities": {
        "cloudflare/clef-omni-20261009": 1341,
        "unreported (error)": 1
      },
      "providers": {
        "Cloudflare": 1341,
        "unreported": 1
      },
      "model_id": "clef_omni",
      "label": "Cloudflare Clef Omni",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9302325581395349,
          "accuracy_among_usable": 0.9302325581395349
        },
        "F02": {
          "n": 46,
          "correct": 26,
          "answered": 46,
          "wrong_valid": 20,
          "failed": 0,
          "accuracy": 0.5652173913043478,
          "accuracy_among_usable": 0.5652173913043478
        },
        "F03": {
          "n": 52,
          "correct": 41,
          "answered": 52,
          "wrong_valid": 11,
          "failed": 0,
          "accuracy": 0.7884615384615384,
          "accuracy_among_usable": 0.7884615384615384
        },
        "F04": {
          "n": 54,
          "correct": 41,
          "answered": 54,
          "wrong_valid": 13,
          "failed": 0,
          "accuracy": 0.7592592592592593,
          "accuracy_among_usable": 0.7592592592592593
        },
        "F05": {
          "n": 49,
          "correct": 41,
          "answered": 49,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.8367346938775511,
          "accuracy_among_usable": 0.8367346938775511
        },
        "F06": {
          "n": 40,
          "correct": 33,
          "answered": 40,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.825,
          "accuracy_among_usable": 0.825
        },
        "F07": {
          "n": 76,
          "correct": 36,
          "answered": 76,
          "wrong_valid": 40,
          "failed": 0,
          "accuracy": 0.47368421052631576,
          "accuracy_among_usable": 0.47368421052631576
        },
        "F08": {
          "n": 67,
          "correct": 41,
          "answered": 66,
          "wrong_valid": 25,
          "failed": 1,
          "accuracy": 0.6119402985074627,
          "accuracy_among_usable": 0.6212121212121212
        },
        "F09": {
          "n": 71,
          "correct": 20,
          "answered": 71,
          "wrong_valid": 51,
          "failed": 0,
          "accuracy": 0.28169014084507044,
          "accuracy_among_usable": 0.28169014084507044
        },
        "F10": {
          "n": 74,
          "correct": 37,
          "answered": 74,
          "wrong_valid": 37,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F11": {
          "n": 41,
          "correct": 26,
          "answered": 41,
          "wrong_valid": 15,
          "failed": 0,
          "accuracy": 0.6341463414634146,
          "accuracy_among_usable": 0.6341463414634146
        },
        "F12": {
          "n": 52,
          "correct": 30,
          "answered": 52,
          "wrong_valid": 22,
          "failed": 0,
          "accuracy": 0.5769230769230769,
          "accuracy_among_usable": 0.5769230769230769
        },
        "F13": {
          "n": 48,
          "correct": 11,
          "answered": 48,
          "wrong_valid": 37,
          "failed": 0,
          "accuracy": 0.22916666666666666,
          "accuracy_among_usable": 0.22916666666666666
        },
        "F14": {
          "n": 42,
          "correct": 32,
          "answered": 42,
          "wrong_valid": 10,
          "failed": 0,
          "accuracy": 0.7619047619047619,
          "accuracy_among_usable": 0.7619047619047619
        },
        "F15": {
          "n": 49,
          "correct": 20,
          "answered": 49,
          "wrong_valid": 29,
          "failed": 0,
          "accuracy": 0.40816326530612246,
          "accuracy_among_usable": 0.40816326530612246
        },
        "F16": {
          "n": 50,
          "correct": 21,
          "answered": 50,
          "wrong_valid": 29,
          "failed": 0,
          "accuracy": 0.42,
          "accuracy_among_usable": 0.42
        },
        "F17": {
          "n": 50,
          "correct": 38,
          "answered": 50,
          "wrong_valid": 12,
          "failed": 0,
          "accuracy": 0.76,
          "accuracy_among_usable": 0.76
        },
        "F18": {
          "n": 50,
          "correct": 20,
          "answered": 50,
          "wrong_valid": 30,
          "failed": 0,
          "accuracy": 0.4,
          "accuracy_among_usable": 0.4
        },
        "F19": {
          "n": 58,
          "correct": 50,
          "answered": 58,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.8620689655172413,
          "accuracy_among_usable": 0.8620689655172413
        },
        "F20": {
          "n": 43,
          "correct": 30,
          "answered": 43,
          "wrong_valid": 13,
          "failed": 0,
          "accuracy": 0.6976744186046512,
          "accuracy_among_usable": 0.6976744186046512
        },
        "F21": {
          "n": 43,
          "correct": 37,
          "answered": 43,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.8604651162790697,
          "accuracy_among_usable": 0.8604651162790697
        },
        "F22": {
          "n": 51,
          "correct": 43,
          "answered": 51,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.8431372549019608,
          "accuracy_among_usable": 0.8431372549019608
        },
        "F23": {
          "n": 52,
          "correct": 46,
          "answered": 52,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.8846153846153846,
          "accuracy_among_usable": 0.8846153846153846
        },
        "F24": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8837209302325582,
          "accuracy_among_usable": 0.8837209302325582
        },
        "F25": {
          "n": 50,
          "correct": 42,
          "answered": 50,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.84,
          "accuracy_among_usable": 0.84
        },
        "F26": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F27": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F28": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F29": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F30": {
          "n": 8,
          "correct": 2,
          "answered": 8,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F31": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        }
      },
      "macro_family_accuracy": 0.6172324604301932,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 849,
        "answered": 1304,
        "wrong_valid": 455,
        "failed": 1,
        "accuracy": 0.6505747126436782,
        "accuracy_among_usable": 0.6510736196319018
      },
      "new_domains": {
        "n": 48,
        "correct": 20,
        "answered": 48,
        "wrong_valid": 28,
        "failed": 0,
        "accuracy": 0.4166666666666667,
        "accuracy_among_usable": 0.4166666666666667
      }
    },
    "solar_flash": {
      "n": 1342,
      "correct": 538,
      "answered": 1340,
      "wrong_valid": 802,
      "failed": 2,
      "accuracy": 0.4008941877794337,
      "accuracy_among_usable": 0.4014925373134328,
      "eventual": {
        "n": 1342,
        "correct": 539,
        "answered": 1342,
        "wrong_valid": 803,
        "failed": 0,
        "accuracy": 0.4016393442622951,
        "accuracy_among_usable": 0.4016393442622951
      },
      "median_ms": 539.9097080226056,
      "p95_ms": 746.6297103848774,
      "attempts": 1344,
      "recoveries": 2,
      "first_statuses": {
        "ok": 1340,
        "provider_failure": 2
      },
      "model_output_failures": 0,
      "probability_warnings": 285,
      "cost": {
        "known_usd": 0.04053205,
        "known_decimal": "0.04053205",
        "unknown_attempts": 2,
        "exact_usd": null,
        "cost_sources": {
          "api_reported": 1342,
          "unreported": 2
        },
        "known_usd_per_1000": 0.030202719821162443
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 56,
          "correct": 51,
          "answered": 56,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.9107142857142857,
          "accuracy_among_usable": 0.9107142857142857
        },
        "0.9": {
          "n": 32,
          "correct": 32,
          "answered": 32,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        },
        "0.95": {
          "n": 17,
          "correct": 17,
          "answered": 17,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        }
      },
      "latency_first_usable": {
        "n": 1340,
        "median_ms": 539.9481870117597,
        "p95_ms": 746.8044103821738
      },
      "provider_failures": 2,
      "dates_toronto": {
        "2026-10-18": 1136,
        "2026-10-19": 206
      },
      "returned_identities": {
        "upstage/solar-decide-flash-20261008": 1340,
        "unreported (error)": 2
      },
      "providers": {
        "Upstage": 1340,
        "unreported": 2
      },
      "model_id": "solar_flash",
      "label": "Solar Decide Flash",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 27,
          "answered": 43,
          "wrong_valid": 16,
          "failed": 0,
          "accuracy": 0.627906976744186,
          "accuracy_among_usable": 0.627906976744186
        },
        "F02": {
          "n": 46,
          "correct": 22,
          "answered": 46,
          "wrong_valid": 24,
          "failed": 0,
          "accuracy": 0.4782608695652174,
          "accuracy_among_usable": 0.4782608695652174
        },
        "F03": {
          "n": 52,
          "correct": 15,
          "answered": 52,
          "wrong_valid": 37,
          "failed": 0,
          "accuracy": 0.28846153846153844,
          "accuracy_among_usable": 0.28846153846153844
        },
        "F04": {
          "n": 54,
          "correct": 14,
          "answered": 54,
          "wrong_valid": 40,
          "failed": 0,
          "accuracy": 0.25925925925925924,
          "accuracy_among_usable": 0.25925925925925924
        },
        "F05": {
          "n": 49,
          "correct": 36,
          "answered": 49,
          "wrong_valid": 13,
          "failed": 0,
          "accuracy": 0.7346938775510204,
          "accuracy_among_usable": 0.7346938775510204
        },
        "F06": {
          "n": 40,
          "correct": 34,
          "answered": 40,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.85,
          "accuracy_among_usable": 0.85
        },
        "F07": {
          "n": 76,
          "correct": 19,
          "answered": 75,
          "wrong_valid": 56,
          "failed": 1,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25333333333333335
        },
        "F08": {
          "n": 67,
          "correct": 26,
          "answered": 67,
          "wrong_valid": 41,
          "failed": 0,
          "accuracy": 0.3880597014925373,
          "accuracy_among_usable": 0.3880597014925373
        },
        "F09": {
          "n": 71,
          "correct": 8,
          "answered": 71,
          "wrong_valid": 63,
          "failed": 0,
          "accuracy": 0.11267605633802817,
          "accuracy_among_usable": 0.11267605633802817
        },
        "F10": {
          "n": 74,
          "correct": 23,
          "answered": 74,
          "wrong_valid": 51,
          "failed": 0,
          "accuracy": 0.3108108108108108,
          "accuracy_among_usable": 0.3108108108108108
        },
        "F11": {
          "n": 41,
          "correct": 8,
          "answered": 41,
          "wrong_valid": 33,
          "failed": 0,
          "accuracy": 0.1951219512195122,
          "accuracy_among_usable": 0.1951219512195122
        },
        "F12": {
          "n": 52,
          "correct": 14,
          "answered": 52,
          "wrong_valid": 38,
          "failed": 0,
          "accuracy": 0.2692307692307692,
          "accuracy_among_usable": 0.2692307692307692
        },
        "F13": {
          "n": 48,
          "correct": 10,
          "answered": 48,
          "wrong_valid": 38,
          "failed": 0,
          "accuracy": 0.20833333333333334,
          "accuracy_among_usable": 0.20833333333333334
        },
        "F14": {
          "n": 42,
          "correct": 17,
          "answered": 42,
          "wrong_valid": 25,
          "failed": 0,
          "accuracy": 0.40476190476190477,
          "accuracy_among_usable": 0.40476190476190477
        },
        "F15": {
          "n": 49,
          "correct": 13,
          "answered": 49,
          "wrong_valid": 36,
          "failed": 0,
          "accuracy": 0.2653061224489796,
          "accuracy_among_usable": 0.2653061224489796
        },
        "F16": {
          "n": 50,
          "correct": 21,
          "answered": 50,
          "wrong_valid": 29,
          "failed": 0,
          "accuracy": 0.42,
          "accuracy_among_usable": 0.42
        },
        "F17": {
          "n": 50,
          "correct": 19,
          "answered": 50,
          "wrong_valid": 31,
          "failed": 0,
          "accuracy": 0.38,
          "accuracy_among_usable": 0.38
        },
        "F18": {
          "n": 50,
          "correct": 10,
          "answered": 50,
          "wrong_valid": 40,
          "failed": 0,
          "accuracy": 0.2,
          "accuracy_among_usable": 0.2
        },
        "F19": {
          "n": 58,
          "correct": 28,
          "answered": 58,
          "wrong_valid": 30,
          "failed": 0,
          "accuracy": 0.4827586206896552,
          "accuracy_among_usable": 0.4827586206896552
        },
        "F20": {
          "n": 43,
          "correct": 16,
          "answered": 43,
          "wrong_valid": 27,
          "failed": 0,
          "accuracy": 0.37209302325581395,
          "accuracy_among_usable": 0.37209302325581395
        },
        "F21": {
          "n": 43,
          "correct": 33,
          "answered": 43,
          "wrong_valid": 10,
          "failed": 0,
          "accuracy": 0.7674418604651163,
          "accuracy_among_usable": 0.7674418604651163
        },
        "F22": {
          "n": 51,
          "correct": 32,
          "answered": 51,
          "wrong_valid": 19,
          "failed": 0,
          "accuracy": 0.6274509803921569,
          "accuracy_among_usable": 0.6274509803921569
        },
        "F23": {
          "n": 52,
          "correct": 29,
          "answered": 52,
          "wrong_valid": 23,
          "failed": 0,
          "accuracy": 0.5576923076923077,
          "accuracy_among_usable": 0.5576923076923077
        },
        "F24": {
          "n": 43,
          "correct": 23,
          "answered": 42,
          "wrong_valid": 19,
          "failed": 1,
          "accuracy": 0.5348837209302325,
          "accuracy_among_usable": 0.5476190476190477
        },
        "F25": {
          "n": 50,
          "correct": 28,
          "answered": 50,
          "wrong_valid": 22,
          "failed": 0,
          "accuracy": 0.56,
          "accuracy_among_usable": 0.56
        },
        "F26": {
          "n": 8,
          "correct": 1,
          "answered": 8,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.125,
          "accuracy_among_usable": 0.125
        },
        "F27": {
          "n": 8,
          "correct": 2,
          "answered": 8,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F28": {
          "n": 8,
          "correct": 0,
          "answered": 8,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.0,
          "accuracy_among_usable": 0.0
        },
        "F29": {
          "n": 8,
          "correct": 2,
          "answered": 8,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F30": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F31": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        }
      },
      "macro_family_accuracy": 0.39258721563362514,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 531,
        "answered": 1304,
        "wrong_valid": 773,
        "failed": 1,
        "accuracy": 0.4068965517241379,
        "accuracy_among_usable": 0.4072085889570552
      },
      "new_domains": {
        "n": 48,
        "correct": 13,
        "answered": 48,
        "wrong_valid": 35,
        "failed": 0,
        "accuracy": 0.2708333333333333,
        "accuracy_among_usable": 0.2708333333333333
      }
    },
    "drex20": {
      "n": 1342,
      "correct": 915,
      "answered": 1302,
      "wrong_valid": 387,
      "failed": 40,
      "accuracy": 0.6818181818181818,
      "accuracy_among_usable": 0.7027649769585254,
      "eventual": {
        "n": 1342,
        "correct": 933,
        "answered": 1337,
        "wrong_valid": 404,
        "failed": 5,
        "accuracy": 0.6952309985096871,
        "accuracy_among_usable": 0.6978309648466716
      },
      "median_ms": 231.8915204377845,
      "p95_ms": 754.8576059227344,
      "attempts": 1382,
      "recoveries": 40,
      "first_statuses": {
        "ok": 1302,
        "provider_failure": 40
      },
      "model_output_failures": 0,
      "probability_warnings": 540,
      "cost": {
        "known_usd": 0.02235882,
        "known_decimal": "0.02235882",
        "unknown_attempts": 45,
        "exact_usd": null,
        "cost_sources": {
          "api_reported": 1337,
          "unreported": 45
        },
        "known_usd_per_1000": 0.016660819672131146
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 558,
          "correct": 550,
          "answered": 558,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.985663082437276,
          "accuracy_among_usable": 0.985663082437276
        },
        "0.9": {
          "n": 488,
          "correct": 486,
          "answered": 488,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.9959016393442623,
          "accuracy_among_usable": 0.9959016393442623
        },
        "0.95": {
          "n": 434,
          "correct": 434,
          "answered": 434,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        }
      },
      "latency_first_usable": {
        "n": 1302,
        "median_ms": 233.71191648766398,
        "p95_ms": 761.6356104030277
      },
      "provider_failures": 40,
      "dates_toronto": {
        "2026-10-18": 1136,
        "2026-10-19": 206
      },
      "returned_identities": {
        "nace-ai/drex-v2.0-20261009": 1302,
        "unreported (error)": 40
      },
      "providers": {
        "DeepInfra": 1302,
        "unreported": 40
      },
      "model_id": "drex20",
      "label": "Drex v2.0",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 39,
          "answered": 43,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9069767441860465,
          "accuracy_among_usable": 0.9069767441860465
        },
        "F02": {
          "n": 46,
          "correct": 33,
          "answered": 43,
          "wrong_valid": 10,
          "failed": 3,
          "accuracy": 0.717391304347826,
          "accuracy_among_usable": 0.7674418604651163
        },
        "F03": {
          "n": 52,
          "correct": 27,
          "answered": 50,
          "wrong_valid": 23,
          "failed": 2,
          "accuracy": 0.5192307692307693,
          "accuracy_among_usable": 0.54
        },
        "F04": {
          "n": 54,
          "correct": 44,
          "answered": 52,
          "wrong_valid": 8,
          "failed": 2,
          "accuracy": 0.8148148148148148,
          "accuracy_among_usable": 0.8461538461538461
        },
        "F05": {
          "n": 49,
          "correct": 43,
          "answered": 48,
          "wrong_valid": 5,
          "failed": 1,
          "accuracy": 0.8775510204081632,
          "accuracy_among_usable": 0.8958333333333334
        },
        "F06": {
          "n": 40,
          "correct": 37,
          "answered": 38,
          "wrong_valid": 1,
          "failed": 2,
          "accuracy": 0.925,
          "accuracy_among_usable": 0.9736842105263158
        },
        "F07": {
          "n": 76,
          "correct": 50,
          "answered": 75,
          "wrong_valid": 25,
          "failed": 1,
          "accuracy": 0.6578947368421053,
          "accuracy_among_usable": 0.6666666666666666
        },
        "F08": {
          "n": 67,
          "correct": 43,
          "answered": 64,
          "wrong_valid": 21,
          "failed": 3,
          "accuracy": 0.6417910447761194,
          "accuracy_among_usable": 0.671875
        },
        "F09": {
          "n": 71,
          "correct": 27,
          "answered": 68,
          "wrong_valid": 41,
          "failed": 3,
          "accuracy": 0.38028169014084506,
          "accuracy_among_usable": 0.39705882352941174
        },
        "F10": {
          "n": 74,
          "correct": 37,
          "answered": 69,
          "wrong_valid": 32,
          "failed": 5,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5362318840579711
        },
        "F11": {
          "n": 41,
          "correct": 33,
          "answered": 41,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.8048780487804879,
          "accuracy_among_usable": 0.8048780487804879
        },
        "F12": {
          "n": 52,
          "correct": 28,
          "answered": 50,
          "wrong_valid": 22,
          "failed": 2,
          "accuracy": 0.5384615384615384,
          "accuracy_among_usable": 0.56
        },
        "F13": {
          "n": 48,
          "correct": 12,
          "answered": 46,
          "wrong_valid": 34,
          "failed": 2,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.2608695652173913
        },
        "F14": {
          "n": 42,
          "correct": 33,
          "answered": 41,
          "wrong_valid": 8,
          "failed": 1,
          "accuracy": 0.7857142857142857,
          "accuracy_among_usable": 0.8048780487804879
        },
        "F15": {
          "n": 49,
          "correct": 26,
          "answered": 48,
          "wrong_valid": 22,
          "failed": 1,
          "accuracy": 0.5306122448979592,
          "accuracy_among_usable": 0.5416666666666666
        },
        "F16": {
          "n": 50,
          "correct": 26,
          "answered": 49,
          "wrong_valid": 23,
          "failed": 1,
          "accuracy": 0.52,
          "accuracy_among_usable": 0.5306122448979592
        },
        "F17": {
          "n": 50,
          "correct": 25,
          "answered": 48,
          "wrong_valid": 23,
          "failed": 2,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5208333333333334
        },
        "F18": {
          "n": 50,
          "correct": 36,
          "answered": 50,
          "wrong_valid": 14,
          "failed": 0,
          "accuracy": 0.72,
          "accuracy_among_usable": 0.72
        },
        "F19": {
          "n": 58,
          "correct": 48,
          "answered": 58,
          "wrong_valid": 10,
          "failed": 0,
          "accuracy": 0.8275862068965517,
          "accuracy_among_usable": 0.8275862068965517
        },
        "F20": {
          "n": 43,
          "correct": 33,
          "answered": 43,
          "wrong_valid": 10,
          "failed": 0,
          "accuracy": 0.7674418604651163,
          "accuracy_among_usable": 0.7674418604651163
        },
        "F21": {
          "n": 43,
          "correct": 42,
          "answered": 43,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9767441860465116,
          "accuracy_among_usable": 0.9767441860465116
        },
        "F22": {
          "n": 51,
          "correct": 42,
          "answered": 47,
          "wrong_valid": 5,
          "failed": 4,
          "accuracy": 0.8235294117647058,
          "accuracy_among_usable": 0.8936170212765957
        },
        "F23": {
          "n": 52,
          "correct": 47,
          "answered": 50,
          "wrong_valid": 3,
          "failed": 2,
          "accuracy": 0.9038461538461539,
          "accuracy_among_usable": 0.94
        },
        "F24": {
          "n": 43,
          "correct": 37,
          "answered": 42,
          "wrong_valid": 5,
          "failed": 1,
          "accuracy": 0.8604651162790697,
          "accuracy_among_usable": 0.8809523809523809
        },
        "F25": {
          "n": 50,
          "correct": 44,
          "answered": 48,
          "wrong_valid": 4,
          "failed": 2,
          "accuracy": 0.88,
          "accuracy_among_usable": 0.9166666666666666
        },
        "F26": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F27": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F28": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F29": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F30": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F31": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        }
      },
      "macro_family_accuracy": 0.6614584250935184,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 900,
        "answered": 1265,
        "wrong_valid": 365,
        "failed": 40,
        "accuracy": 0.6896551724137931,
        "accuracy_among_usable": 0.7114624505928854
      },
      "new_domains": {
        "n": 48,
        "correct": 23,
        "answered": 48,
        "wrong_valid": 25,
        "failed": 0,
        "accuracy": 0.4791666666666667,
        "accuracy_among_usable": 0.4791666666666667
      }
    },
    "drex15": {
      "n": 1342,
      "correct": 853,
      "answered": 1342,
      "wrong_valid": 489,
      "failed": 0,
      "accuracy": 0.6356184798807749,
      "accuracy_among_usable": 0.6356184798807749,
      "eventual": {
        "n": 1342,
        "correct": 853,
        "answered": 1342,
        "wrong_valid": 489,
        "failed": 0,
        "accuracy": 0.6356184798807749,
        "accuracy_among_usable": 0.6356184798807749
      },
      "median_ms": 203.44412501435727,
      "p95_ms": 648.9552770508458,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "model_output_failures": 0,
      "probability_warnings": 569,
      "cost": {
        "known_usd": 0.01497636,
        "known_decimal": "0.01497636",
        "unknown_attempts": 0,
        "exact_usd": 0.01497636,
        "cost_sources": {
          "api_reported": 1342
        },
        "known_usd_per_1000": 0.01115973174366617
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 700,
          "correct": 612,
          "answered": 700,
          "wrong_valid": 88,
          "failed": 0,
          "accuracy": 0.8742857142857143,
          "accuracy_among_usable": 0.8742857142857143
        },
        "0.9": {
          "n": 606,
          "correct": 554,
          "answered": 606,
          "wrong_valid": 52,
          "failed": 0,
          "accuracy": 0.9141914191419142,
          "accuracy_among_usable": 0.9141914191419142
        },
        "0.95": {
          "n": 538,
          "correct": 503,
          "answered": 538,
          "wrong_valid": 35,
          "failed": 0,
          "accuracy": 0.9349442379182156,
          "accuracy_among_usable": 0.9349442379182156
        }
      },
      "latency_first_usable": {
        "n": 1342,
        "median_ms": 203.44412501435727,
        "p95_ms": 648.9552770508458
      },
      "provider_failures": 0,
      "dates_toronto": {
        "2026-10-18": 1136,
        "2026-10-19": 206
      },
      "returned_identities": {
        "nace-ai/drex-v1.5-20261009": 1342
      },
      "providers": {
        "DeepInfra": 1342
      },
      "model_id": "drex15",
      "label": "Drex v1.5",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8837209302325582,
          "accuracy_among_usable": 0.8837209302325582
        },
        "F02": {
          "n": 46,
          "correct": 26,
          "answered": 46,
          "wrong_valid": 20,
          "failed": 0,
          "accuracy": 0.5652173913043478,
          "accuracy_among_usable": 0.5652173913043478
        },
        "F03": {
          "n": 52,
          "correct": 26,
          "answered": 52,
          "wrong_valid": 26,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F04": {
          "n": 54,
          "correct": 36,
          "answered": 54,
          "wrong_valid": 18,
          "failed": 0,
          "accuracy": 0.6666666666666666,
          "accuracy_among_usable": 0.6666666666666666
        },
        "F05": {
          "n": 49,
          "correct": 41,
          "answered": 49,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.8367346938775511,
          "accuracy_among_usable": 0.8367346938775511
        },
        "F06": {
          "n": 40,
          "correct": 37,
          "answered": 40,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.925,
          "accuracy_among_usable": 0.925
        },
        "F07": {
          "n": 76,
          "correct": 51,
          "answered": 76,
          "wrong_valid": 25,
          "failed": 0,
          "accuracy": 0.6710526315789473,
          "accuracy_among_usable": 0.6710526315789473
        },
        "F08": {
          "n": 67,
          "correct": 48,
          "answered": 67,
          "wrong_valid": 19,
          "failed": 0,
          "accuracy": 0.7164179104477612,
          "accuracy_among_usable": 0.7164179104477612
        },
        "F09": {
          "n": 71,
          "correct": 33,
          "answered": 71,
          "wrong_valid": 38,
          "failed": 0,
          "accuracy": 0.4647887323943662,
          "accuracy_among_usable": 0.4647887323943662
        },
        "F10": {
          "n": 74,
          "correct": 30,
          "answered": 74,
          "wrong_valid": 44,
          "failed": 0,
          "accuracy": 0.40540540540540543,
          "accuracy_among_usable": 0.40540540540540543
        },
        "F11": {
          "n": 41,
          "correct": 21,
          "answered": 41,
          "wrong_valid": 20,
          "failed": 0,
          "accuracy": 0.5121951219512195,
          "accuracy_among_usable": 0.5121951219512195
        },
        "F12": {
          "n": 52,
          "correct": 23,
          "answered": 52,
          "wrong_valid": 29,
          "failed": 0,
          "accuracy": 0.4423076923076923,
          "accuracy_among_usable": 0.4423076923076923
        },
        "F13": {
          "n": 48,
          "correct": 13,
          "answered": 48,
          "wrong_valid": 35,
          "failed": 0,
          "accuracy": 0.2708333333333333,
          "accuracy_among_usable": 0.2708333333333333
        },
        "F14": {
          "n": 42,
          "correct": 28,
          "answered": 42,
          "wrong_valid": 14,
          "failed": 0,
          "accuracy": 0.6666666666666666,
          "accuracy_among_usable": 0.6666666666666666
        },
        "F15": {
          "n": 49,
          "correct": 26,
          "answered": 49,
          "wrong_valid": 23,
          "failed": 0,
          "accuracy": 0.5306122448979592,
          "accuracy_among_usable": 0.5306122448979592
        },
        "F16": {
          "n": 50,
          "correct": 23,
          "answered": 50,
          "wrong_valid": 27,
          "failed": 0,
          "accuracy": 0.46,
          "accuracy_among_usable": 0.46
        },
        "F17": {
          "n": 50,
          "correct": 29,
          "answered": 50,
          "wrong_valid": 21,
          "failed": 0,
          "accuracy": 0.58,
          "accuracy_among_usable": 0.58
        },
        "F18": {
          "n": 50,
          "correct": 22,
          "answered": 50,
          "wrong_valid": 28,
          "failed": 0,
          "accuracy": 0.44,
          "accuracy_among_usable": 0.44
        },
        "F19": {
          "n": 58,
          "correct": 48,
          "answered": 58,
          "wrong_valid": 10,
          "failed": 0,
          "accuracy": 0.8275862068965517,
          "accuracy_among_usable": 0.8275862068965517
        },
        "F20": {
          "n": 43,
          "correct": 27,
          "answered": 43,
          "wrong_valid": 16,
          "failed": 0,
          "accuracy": 0.627906976744186,
          "accuracy_among_usable": 0.627906976744186
        },
        "F21": {
          "n": 43,
          "correct": 39,
          "answered": 43,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9069767441860465,
          "accuracy_among_usable": 0.9069767441860465
        },
        "F22": {
          "n": 51,
          "correct": 44,
          "answered": 51,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.8627450980392157,
          "accuracy_among_usable": 0.8627450980392157
        },
        "F23": {
          "n": 52,
          "correct": 46,
          "answered": 52,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.8846153846153846,
          "accuracy_among_usable": 0.8846153846153846
        },
        "F24": {
          "n": 43,
          "correct": 39,
          "answered": 43,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9069767441860465,
          "accuracy_among_usable": 0.9069767441860465
        },
        "F25": {
          "n": 50,
          "correct": 41,
          "answered": 50,
          "wrong_valid": 9,
          "failed": 0,
          "accuracy": 0.82,
          "accuracy_among_usable": 0.82
        },
        "F26": {
          "n": 8,
          "correct": 1,
          "answered": 8,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.125,
          "accuracy_among_usable": 0.125
        },
        "F27": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.625,
          "accuracy_among_usable": 0.625
        },
        "F28": {
          "n": 8,
          "correct": 2,
          "answered": 8,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F29": {
          "n": 8,
          "correct": 2,
          "answered": 8,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F30": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F31": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        }
      },
      "macro_family_accuracy": 0.6007879540558678,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 843,
        "answered": 1305,
        "wrong_valid": 462,
        "failed": 0,
        "accuracy": 0.6459770114942529,
        "accuracy_among_usable": 0.6459770114942529
      },
      "new_domains": {
        "n": 48,
        "correct": 18,
        "answered": 48,
        "wrong_valid": 30,
        "failed": 0,
        "accuracy": 0.375,
        "accuracy_among_usable": 0.375
      }
    },
    "classify1": {
      "n": 1342,
      "correct": 550,
      "answered": 1342,
      "wrong_valid": 792,
      "failed": 0,
      "accuracy": 0.4098360655737705,
      "accuracy_among_usable": 0.4098360655737705,
      "eventual": {
        "n": 1342,
        "correct": 550,
        "answered": 1342,
        "wrong_valid": 792,
        "failed": 0,
        "accuracy": 0.4098360655737705,
        "accuracy_among_usable": 0.4098360655737705
      },
      "median_ms": 268.4367289766669,
      "p95_ms": 361.68582041864283,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "model_output_failures": 0,
      "probability_warnings": 0,
      "cost": {
        "known_usd": 0.0287026,
        "known_decimal": "0.02870260",
        "unknown_attempts": 0,
        "exact_usd": 0.0287026,
        "cost_sources": {
          "api_reported": 1342
        },
        "known_usd_per_1000": 0.021387928464977647
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 68,
          "correct": 67,
          "answered": 68,
          "wrong_valid": 1,
          "failed": 0,
          "accuracy": 0.9852941176470589,
          "accuracy_among_usable": 0.9852941176470589
        },
        "0.9": {
          "n": 24,
          "correct": 24,
          "answered": 24,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        },
        "0.95": {
          "n": 6,
          "correct": 6,
          "answered": 6,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        }
      },
      "latency_first_usable": {
        "n": 1342,
        "median_ms": 268.4367289766669,
        "p95_ms": 361.68582041864283
      },
      "provider_failures": 0,
      "dates_toronto": {
        "2026-10-18": 1136,
        "2026-10-19": 206
      },
      "returned_identities": {
        "scaledown/classify-1-20260928": 1342
      },
      "providers": {
        "ScaleDown": 1342
      },
      "model_id": "classify1",
      "label": "ScaleDown Classify-1",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 31,
          "answered": 43,
          "wrong_valid": 12,
          "failed": 0,
          "accuracy": 0.7209302325581395,
          "accuracy_among_usable": 0.7209302325581395
        },
        "F02": {
          "n": 46,
          "correct": 18,
          "answered": 46,
          "wrong_valid": 28,
          "failed": 0,
          "accuracy": 0.391304347826087,
          "accuracy_among_usable": 0.391304347826087
        },
        "F03": {
          "n": 52,
          "correct": 13,
          "answered": 52,
          "wrong_valid": 39,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F04": {
          "n": 54,
          "correct": 17,
          "answered": 54,
          "wrong_valid": 37,
          "failed": 0,
          "accuracy": 0.3148148148148148,
          "accuracy_among_usable": 0.3148148148148148
        },
        "F05": {
          "n": 49,
          "correct": 28,
          "answered": 49,
          "wrong_valid": 21,
          "failed": 0,
          "accuracy": 0.5714285714285714,
          "accuracy_among_usable": 0.5714285714285714
        },
        "F06": {
          "n": 40,
          "correct": 34,
          "answered": 40,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.85,
          "accuracy_among_usable": 0.85
        },
        "F07": {
          "n": 76,
          "correct": 26,
          "answered": 76,
          "wrong_valid": 50,
          "failed": 0,
          "accuracy": 0.34210526315789475,
          "accuracy_among_usable": 0.34210526315789475
        },
        "F08": {
          "n": 67,
          "correct": 29,
          "answered": 67,
          "wrong_valid": 38,
          "failed": 0,
          "accuracy": 0.43283582089552236,
          "accuracy_among_usable": 0.43283582089552236
        },
        "F09": {
          "n": 71,
          "correct": 22,
          "answered": 71,
          "wrong_valid": 49,
          "failed": 0,
          "accuracy": 0.30985915492957744,
          "accuracy_among_usable": 0.30985915492957744
        },
        "F10": {
          "n": 74,
          "correct": 15,
          "answered": 74,
          "wrong_valid": 59,
          "failed": 0,
          "accuracy": 0.20270270270270271,
          "accuracy_among_usable": 0.20270270270270271
        },
        "F11": {
          "n": 41,
          "correct": 17,
          "answered": 41,
          "wrong_valid": 24,
          "failed": 0,
          "accuracy": 0.4146341463414634,
          "accuracy_among_usable": 0.4146341463414634
        },
        "F12": {
          "n": 52,
          "correct": 8,
          "answered": 52,
          "wrong_valid": 44,
          "failed": 0,
          "accuracy": 0.15384615384615385,
          "accuracy_among_usable": 0.15384615384615385
        },
        "F13": {
          "n": 48,
          "correct": 11,
          "answered": 48,
          "wrong_valid": 37,
          "failed": 0,
          "accuracy": 0.22916666666666666,
          "accuracy_among_usable": 0.22916666666666666
        },
        "F14": {
          "n": 42,
          "correct": 13,
          "answered": 42,
          "wrong_valid": 29,
          "failed": 0,
          "accuracy": 0.30952380952380953,
          "accuracy_among_usable": 0.30952380952380953
        },
        "F15": {
          "n": 49,
          "correct": 17,
          "answered": 49,
          "wrong_valid": 32,
          "failed": 0,
          "accuracy": 0.3469387755102041,
          "accuracy_among_usable": 0.3469387755102041
        },
        "F16": {
          "n": 50,
          "correct": 19,
          "answered": 50,
          "wrong_valid": 31,
          "failed": 0,
          "accuracy": 0.38,
          "accuracy_among_usable": 0.38
        },
        "F17": {
          "n": 50,
          "correct": 21,
          "answered": 50,
          "wrong_valid": 29,
          "failed": 0,
          "accuracy": 0.42,
          "accuracy_among_usable": 0.42
        },
        "F18": {
          "n": 50,
          "correct": 12,
          "answered": 50,
          "wrong_valid": 38,
          "failed": 0,
          "accuracy": 0.24,
          "accuracy_among_usable": 0.24
        },
        "F19": {
          "n": 58,
          "correct": 28,
          "answered": 58,
          "wrong_valid": 30,
          "failed": 0,
          "accuracy": 0.4827586206896552,
          "accuracy_among_usable": 0.4827586206896552
        },
        "F20": {
          "n": 43,
          "correct": 14,
          "answered": 43,
          "wrong_valid": 29,
          "failed": 0,
          "accuracy": 0.32558139534883723,
          "accuracy_among_usable": 0.32558139534883723
        },
        "F21": {
          "n": 43,
          "correct": 31,
          "answered": 43,
          "wrong_valid": 12,
          "failed": 0,
          "accuracy": 0.7209302325581395,
          "accuracy_among_usable": 0.7209302325581395
        },
        "F22": {
          "n": 51,
          "correct": 29,
          "answered": 51,
          "wrong_valid": 22,
          "failed": 0,
          "accuracy": 0.5686274509803921,
          "accuracy_among_usable": 0.5686274509803921
        },
        "F23": {
          "n": 52,
          "correct": 30,
          "answered": 52,
          "wrong_valid": 22,
          "failed": 0,
          "accuracy": 0.5769230769230769,
          "accuracy_among_usable": 0.5769230769230769
        },
        "F24": {
          "n": 43,
          "correct": 33,
          "answered": 43,
          "wrong_valid": 10,
          "failed": 0,
          "accuracy": 0.7674418604651163,
          "accuracy_among_usable": 0.7674418604651163
        },
        "F25": {
          "n": 50,
          "correct": 25,
          "answered": 50,
          "wrong_valid": 25,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F26": {
          "n": 8,
          "correct": 1,
          "answered": 8,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.125,
          "accuracy_among_usable": 0.125
        },
        "F27": {
          "n": 8,
          "correct": 2,
          "answered": 8,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F28": {
          "n": 8,
          "correct": 1,
          "answered": 8,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.125,
          "accuracy_among_usable": 0.125
        },
        "F29": {
          "n": 8,
          "correct": 1,
          "answered": 8,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.125,
          "accuracy_among_usable": 0.125
        },
        "F30": {
          "n": 8,
          "correct": 1,
          "answered": 8,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.125,
          "accuracy_among_usable": 0.125
        },
        "F31": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        }
      },
      "macro_family_accuracy": 0.38539848700538143,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 542,
        "answered": 1305,
        "wrong_valid": 763,
        "failed": 0,
        "accuracy": 0.4153256704980843,
        "accuracy_among_usable": 0.4153256704980843
      },
      "new_domains": {
        "n": 48,
        "correct": 9,
        "answered": 48,
        "wrong_valid": 39,
        "failed": 0,
        "accuracy": 0.1875,
        "accuracy_among_usable": 0.1875
      }
    },
    "kev4b": {
      "n": 1342,
      "correct": 822,
      "answered": 1342,
      "wrong_valid": 520,
      "failed": 0,
      "accuracy": 0.6125186289120715,
      "accuracy_among_usable": 0.6125186289120715,
      "eventual": {
        "n": 1342,
        "correct": 822,
        "answered": 1342,
        "wrong_valid": 520,
        "failed": 0,
        "accuracy": 0.6125186289120715,
        "accuracy_among_usable": 0.6125186289120715
      },
      "median_ms": 224.8376039788127,
      "p95_ms": 377.38076279056264,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "model_output_failures": 0,
      "probability_warnings": 536,
      "cost": {
        "known_usd": 0.015725178,
        "known_decimal": "0.015725178",
        "unknown_attempts": 0,
        "exact_usd": 0.015725178,
        "cost_sources": {
          "api_reported": 1342
        },
        "known_usd_per_1000": 0.011717718330849477
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 230,
          "correct": 228,
          "answered": 230,
          "wrong_valid": 2,
          "failed": 0,
          "accuracy": 0.991304347826087,
          "accuracy_among_usable": 0.991304347826087
        },
        "0.9": {
          "n": 144,
          "correct": 144,
          "answered": 144,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        },
        "0.95": {
          "n": 96,
          "correct": 96,
          "answered": 96,
          "wrong_valid": 0,
          "failed": 0,
          "accuracy": 1.0,
          "accuracy_among_usable": 1.0
        }
      },
      "latency_first_usable": {
        "n": 1342,
        "median_ms": 224.8376039788127,
        "p95_ms": 377.38076279056264
      },
      "provider_failures": 0,
      "dates_toronto": {
        "2026-10-18": 1136,
        "2026-10-19": 206
      },
      "returned_identities": {
        "jaredpalmer/kev-4b-20260924": 1342
      },
      "providers": {
        "Phala": 1342
      },
      "model_id": "kev4b",
      "label": "Kev 4B",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 39,
          "answered": 43,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9069767441860465,
          "accuracy_among_usable": 0.9069767441860465
        },
        "F02": {
          "n": 46,
          "correct": 36,
          "answered": 46,
          "wrong_valid": 10,
          "failed": 0,
          "accuracy": 0.782608695652174,
          "accuracy_among_usable": 0.782608695652174
        },
        "F03": {
          "n": 52,
          "correct": 33,
          "answered": 52,
          "wrong_valid": 19,
          "failed": 0,
          "accuracy": 0.6346153846153846,
          "accuracy_among_usable": 0.6346153846153846
        },
        "F04": {
          "n": 54,
          "correct": 34,
          "answered": 54,
          "wrong_valid": 20,
          "failed": 0,
          "accuracy": 0.6296296296296297,
          "accuracy_among_usable": 0.6296296296296297
        },
        "F05": {
          "n": 49,
          "correct": 42,
          "answered": 49,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.8571428571428571,
          "accuracy_among_usable": 0.8571428571428571
        },
        "F06": {
          "n": 40,
          "correct": 35,
          "answered": 40,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.875,
          "accuracy_among_usable": 0.875
        },
        "F07": {
          "n": 76,
          "correct": 37,
          "answered": 76,
          "wrong_valid": 39,
          "failed": 0,
          "accuracy": 0.4868421052631579,
          "accuracy_among_usable": 0.4868421052631579
        },
        "F08": {
          "n": 67,
          "correct": 45,
          "answered": 67,
          "wrong_valid": 22,
          "failed": 0,
          "accuracy": 0.6716417910447762,
          "accuracy_among_usable": 0.6716417910447762
        },
        "F09": {
          "n": 71,
          "correct": 21,
          "answered": 71,
          "wrong_valid": 50,
          "failed": 0,
          "accuracy": 0.29577464788732394,
          "accuracy_among_usable": 0.29577464788732394
        },
        "F10": {
          "n": 74,
          "correct": 33,
          "answered": 74,
          "wrong_valid": 41,
          "failed": 0,
          "accuracy": 0.44594594594594594,
          "accuracy_among_usable": 0.44594594594594594
        },
        "F11": {
          "n": 41,
          "correct": 30,
          "answered": 41,
          "wrong_valid": 11,
          "failed": 0,
          "accuracy": 0.7317073170731707,
          "accuracy_among_usable": 0.7317073170731707
        },
        "F12": {
          "n": 52,
          "correct": 25,
          "answered": 52,
          "wrong_valid": 27,
          "failed": 0,
          "accuracy": 0.4807692307692308,
          "accuracy_among_usable": 0.4807692307692308
        },
        "F13": {
          "n": 48,
          "correct": 11,
          "answered": 48,
          "wrong_valid": 37,
          "failed": 0,
          "accuracy": 0.22916666666666666,
          "accuracy_among_usable": 0.22916666666666666
        },
        "F14": {
          "n": 42,
          "correct": 31,
          "answered": 42,
          "wrong_valid": 11,
          "failed": 0,
          "accuracy": 0.7380952380952381,
          "accuracy_among_usable": 0.7380952380952381
        },
        "F15": {
          "n": 49,
          "correct": 26,
          "answered": 49,
          "wrong_valid": 23,
          "failed": 0,
          "accuracy": 0.5306122448979592,
          "accuracy_among_usable": 0.5306122448979592
        },
        "F16": {
          "n": 50,
          "correct": 19,
          "answered": 50,
          "wrong_valid": 31,
          "failed": 0,
          "accuracy": 0.38,
          "accuracy_among_usable": 0.38
        },
        "F17": {
          "n": 50,
          "correct": 34,
          "answered": 50,
          "wrong_valid": 16,
          "failed": 0,
          "accuracy": 0.68,
          "accuracy_among_usable": 0.68
        },
        "F18": {
          "n": 50,
          "correct": 29,
          "answered": 50,
          "wrong_valid": 21,
          "failed": 0,
          "accuracy": 0.58,
          "accuracy_among_usable": 0.58
        },
        "F19": {
          "n": 58,
          "correct": 39,
          "answered": 58,
          "wrong_valid": 19,
          "failed": 0,
          "accuracy": 0.6724137931034483,
          "accuracy_among_usable": 0.6724137931034483
        },
        "F20": {
          "n": 43,
          "correct": 24,
          "answered": 43,
          "wrong_valid": 19,
          "failed": 0,
          "accuracy": 0.5581395348837209,
          "accuracy_among_usable": 0.5581395348837209
        },
        "F21": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9302325581395349,
          "accuracy_among_usable": 0.9302325581395349
        },
        "F22": {
          "n": 51,
          "correct": 48,
          "answered": 51,
          "wrong_valid": 3,
          "failed": 0,
          "accuracy": 0.9411764705882353,
          "accuracy_among_usable": 0.9411764705882353
        },
        "F23": {
          "n": 52,
          "correct": 37,
          "answered": 52,
          "wrong_valid": 15,
          "failed": 0,
          "accuracy": 0.7115384615384616,
          "accuracy_among_usable": 0.7115384615384616
        },
        "F24": {
          "n": 43,
          "correct": 20,
          "answered": 43,
          "wrong_valid": 23,
          "failed": 0,
          "accuracy": 0.46511627906976744,
          "accuracy_among_usable": 0.46511627906976744
        },
        "F25": {
          "n": 50,
          "correct": 36,
          "answered": 50,
          "wrong_valid": 14,
          "failed": 0,
          "accuracy": 0.72,
          "accuracy_among_usable": 0.72
        },
        "F26": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F27": {
          "n": 8,
          "correct": 1,
          "answered": 8,
          "wrong_valid": 7,
          "failed": 0,
          "accuracy": 0.125,
          "accuracy_among_usable": 0.125
        },
        "F28": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        },
        "F29": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F30": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F31": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        }
      },
      "macro_family_accuracy": 0.586617599877185,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 807,
        "answered": 1305,
        "wrong_valid": 498,
        "failed": 0,
        "accuracy": 0.6183908045977011,
        "accuracy_among_usable": 0.6183908045977011
      },
      "new_domains": {
        "n": 48,
        "correct": 18,
        "answered": 48,
        "wrong_valid": 30,
        "failed": 0,
        "accuracy": 0.375,
        "accuracy_among_usable": 0.375
      }
    },
    "tev1_4b_native": {
      "n": 1342,
      "correct": 751,
      "answered": 1342,
      "wrong_valid": 591,
      "failed": 0,
      "accuracy": 0.559612518628912,
      "accuracy_among_usable": 0.559612518628912,
      "eventual": {
        "n": 1342,
        "correct": 751,
        "answered": 1342,
        "wrong_valid": 591,
        "failed": 0,
        "accuracy": 0.559612518628912,
        "accuracy_among_usable": 0.559612518628912
      },
      "median_ms": 197.5683750351891,
      "p95_ms": 252.86549585871398,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "model_output_failures": 0,
      "probability_warnings": 0,
      "cost": {
        "known_usd": 0.02101113,
        "known_decimal": "0.021011130",
        "unknown_attempts": 0,
        "exact_usd": 0.02101113,
        "cost_sources": {
          "api_reported": 1342
        },
        "known_usd_per_1000": 0.015656579731743666
      },
      "confidence_diagnostics": {
        "0.8": {
          "n": 425,
          "correct": 390,
          "answered": 425,
          "wrong_valid": 35,
          "failed": 0,
          "accuracy": 0.9176470588235294,
          "accuracy_among_usable": 0.9176470588235294
        },
        "0.9": {
          "n": 317,
          "correct": 302,
          "answered": 317,
          "wrong_valid": 15,
          "failed": 0,
          "accuracy": 0.9526813880126183,
          "accuracy_among_usable": 0.9526813880126183
        },
        "0.95": {
          "n": 259,
          "correct": 248,
          "answered": 259,
          "wrong_valid": 11,
          "failed": 0,
          "accuracy": 0.9575289575289575,
          "accuracy_among_usable": 0.9575289575289575
        }
      },
      "latency_first_usable": {
        "n": 1342,
        "median_ms": 197.5683750351891,
        "p95_ms": 252.86549585871398
      },
      "provider_failures": 0,
      "dates_toronto": {
        "2026-10-18": 1136,
        "2026-10-19": 206
      },
      "returned_identities": {
        "togethercomputer/tev1-4b-experimental-20260923": 1342
      },
      "providers": {
        "Together": 1342
      },
      "model_id": "tev1_4b_native",
      "label": "Tev1 4B experimental (OpenRouter native adapter)",
      "route": "OpenRouter",
      "families": {
        "F01": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.8837209302325582,
          "accuracy_among_usable": 0.8837209302325582
        },
        "F02": {
          "n": 46,
          "correct": 25,
          "answered": 46,
          "wrong_valid": 21,
          "failed": 0,
          "accuracy": 0.5434782608695652,
          "accuracy_among_usable": 0.5434782608695652
        },
        "F03": {
          "n": 52,
          "correct": 29,
          "answered": 52,
          "wrong_valid": 23,
          "failed": 0,
          "accuracy": 0.5576923076923077,
          "accuracy_among_usable": 0.5576923076923077
        },
        "F04": {
          "n": 54,
          "correct": 33,
          "answered": 54,
          "wrong_valid": 21,
          "failed": 0,
          "accuracy": 0.6111111111111112,
          "accuracy_among_usable": 0.6111111111111112
        },
        "F05": {
          "n": 49,
          "correct": 37,
          "answered": 49,
          "wrong_valid": 12,
          "failed": 0,
          "accuracy": 0.7551020408163265,
          "accuracy_among_usable": 0.7551020408163265
        },
        "F06": {
          "n": 40,
          "correct": 32,
          "answered": 40,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.8,
          "accuracy_among_usable": 0.8
        },
        "F07": {
          "n": 76,
          "correct": 28,
          "answered": 76,
          "wrong_valid": 48,
          "failed": 0,
          "accuracy": 0.3684210526315789,
          "accuracy_among_usable": 0.3684210526315789
        },
        "F08": {
          "n": 67,
          "correct": 40,
          "answered": 67,
          "wrong_valid": 27,
          "failed": 0,
          "accuracy": 0.5970149253731343,
          "accuracy_among_usable": 0.5970149253731343
        },
        "F09": {
          "n": 71,
          "correct": 16,
          "answered": 71,
          "wrong_valid": 55,
          "failed": 0,
          "accuracy": 0.22535211267605634,
          "accuracy_among_usable": 0.22535211267605634
        },
        "F10": {
          "n": 74,
          "correct": 25,
          "answered": 74,
          "wrong_valid": 49,
          "failed": 0,
          "accuracy": 0.33783783783783783,
          "accuracy_among_usable": 0.33783783783783783
        },
        "F11": {
          "n": 41,
          "correct": 23,
          "answered": 41,
          "wrong_valid": 18,
          "failed": 0,
          "accuracy": 0.5609756097560976,
          "accuracy_among_usable": 0.5609756097560976
        },
        "F12": {
          "n": 52,
          "correct": 20,
          "answered": 52,
          "wrong_valid": 32,
          "failed": 0,
          "accuracy": 0.38461538461538464,
          "accuracy_among_usable": 0.38461538461538464
        },
        "F13": {
          "n": 48,
          "correct": 15,
          "answered": 48,
          "wrong_valid": 33,
          "failed": 0,
          "accuracy": 0.3125,
          "accuracy_among_usable": 0.3125
        },
        "F14": {
          "n": 42,
          "correct": 27,
          "answered": 42,
          "wrong_valid": 15,
          "failed": 0,
          "accuracy": 0.6428571428571429,
          "accuracy_among_usable": 0.6428571428571429
        },
        "F15": {
          "n": 49,
          "correct": 19,
          "answered": 49,
          "wrong_valid": 30,
          "failed": 0,
          "accuracy": 0.3877551020408163,
          "accuracy_among_usable": 0.3877551020408163
        },
        "F16": {
          "n": 50,
          "correct": 19,
          "answered": 50,
          "wrong_valid": 31,
          "failed": 0,
          "accuracy": 0.38,
          "accuracy_among_usable": 0.38
        },
        "F17": {
          "n": 50,
          "correct": 31,
          "answered": 50,
          "wrong_valid": 19,
          "failed": 0,
          "accuracy": 0.62,
          "accuracy_among_usable": 0.62
        },
        "F18": {
          "n": 50,
          "correct": 20,
          "answered": 50,
          "wrong_valid": 30,
          "failed": 0,
          "accuracy": 0.4,
          "accuracy_among_usable": 0.4
        },
        "F19": {
          "n": 58,
          "correct": 42,
          "answered": 58,
          "wrong_valid": 16,
          "failed": 0,
          "accuracy": 0.7241379310344828,
          "accuracy_among_usable": 0.7241379310344828
        },
        "F20": {
          "n": 43,
          "correct": 28,
          "answered": 43,
          "wrong_valid": 15,
          "failed": 0,
          "accuracy": 0.6511627906976745,
          "accuracy_among_usable": 0.6511627906976745
        },
        "F21": {
          "n": 43,
          "correct": 35,
          "answered": 43,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.813953488372093,
          "accuracy_among_usable": 0.813953488372093
        },
        "F22": {
          "n": 51,
          "correct": 47,
          "answered": 51,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.9215686274509803,
          "accuracy_among_usable": 0.9215686274509803
        },
        "F23": {
          "n": 52,
          "correct": 39,
          "answered": 52,
          "wrong_valid": 13,
          "failed": 0,
          "accuracy": 0.75,
          "accuracy_among_usable": 0.75
        },
        "F24": {
          "n": 43,
          "correct": 29,
          "answered": 43,
          "wrong_valid": 14,
          "failed": 0,
          "accuracy": 0.6744186046511628,
          "accuracy_among_usable": 0.6744186046511628
        },
        "F25": {
          "n": 50,
          "correct": 39,
          "answered": 50,
          "wrong_valid": 11,
          "failed": 0,
          "accuracy": 0.78,
          "accuracy_among_usable": 0.78
        },
        "F26": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F27": {
          "n": 8,
          "correct": 0,
          "answered": 8,
          "wrong_valid": 8,
          "failed": 0,
          "accuracy": 0.0,
          "accuracy_among_usable": 0.0
        },
        "F28": {
          "n": 8,
          "correct": 2,
          "answered": 8,
          "wrong_valid": 6,
          "failed": 0,
          "accuracy": 0.25,
          "accuracy_among_usable": 0.25
        },
        "F29": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F30": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "wrong_valid": 5,
          "failed": 0,
          "accuracy": 0.375,
          "accuracy_among_usable": 0.375
        },
        "F31": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "wrong_valid": 4,
          "failed": 0,
          "accuracy": 0.5,
          "accuracy_among_usable": 0.5
        }
      },
      "macro_family_accuracy": 0.5341508148618164,
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 737,
        "answered": 1305,
        "wrong_valid": 568,
        "failed": 0,
        "accuracy": 0.5647509578544061,
        "accuracy_among_usable": 0.5647509578544061
      },
      "new_domains": {
        "n": 48,
        "correct": 15,
        "answered": 48,
        "wrong_valid": 33,
        "failed": 0,
        "accuracy": 0.3125,
        "accuracy_among_usable": 0.3125
      }
    },
    "reference_sol": {
      "n": 1342,
      "correct": 1143,
      "answered": 1342,
      "failed": 0,
      "wrong_valid": 199,
      "accuracy": 0.8517138599105812,
      "eventual": {
        "n": 1342,
        "correct": 1143,
        "answered": 1342,
        "failed": 0,
        "wrong_valid": 199,
        "accuracy": 0.8517138599105812
      },
      "latency_first_all": {
        "n": 1342,
        "median_ms": 1023.0274999630637,
        "p95_ms": 1546.3492952927484
      },
      "latency_first_usable": {
        "n": 1342,
        "median_ms": 1023.0274999630637,
        "p95_ms": 1546.3492952927484
      },
      "cost_all_attempts": {
        "known_usd": 0.8482945,
        "exact_usd": "0.8482945",
        "reported_attempts": 1342,
        "missing_attempts": 0,
        "known_usd_per_1000": 0.6321121460506706
      },
      "cost_first_attempts": {
        "known_usd": 0.8482945,
        "exact_usd": "0.8482945",
        "reported_attempts": 1342,
        "missing_attempts": 0
      },
      "cost_recovery_attempts": {
        "known_usd": 0.0,
        "exact_usd": "0",
        "reported_attempts": 0,
        "missing_attempts": 0
      },
      "attempts": 1342,
      "recoveries": 0,
      "statuses": {
        "ok": 1342
      },
      "reasoning_token_counts": {
        "0": 1342
      },
      "reasoning_text_responses": 0,
      "reasoning_verification_counts": {
        "explicit_reported_zero": 1342
      },
      "usage": {
        "prompt_tokens": 390314,
        "completion_tokens": 6710,
        "total_tokens": 397024
      },
      "returned_identities": {
        "openai/gpt-6-sol": 1342
      },
      "providers": {
        "OpenAI": 1342
      },
      "dates_toronto": {
        "2026-10-19": 1342
      },
      "families": {
        "F01": {
          "n": 43,
          "correct": 42,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9767441860465116
        },
        "F02": {
          "n": 46,
          "correct": 45,
          "answered": 46,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9782608695652174
        },
        "F03": {
          "n": 52,
          "correct": 52,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 0,
          "accuracy": 1.0
        },
        "F04": {
          "n": 54,
          "correct": 53,
          "answered": 54,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9814814814814815
        },
        "F05": {
          "n": 49,
          "correct": 46,
          "answered": 49,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9387755102040817
        },
        "F06": {
          "n": 40,
          "correct": 38,
          "answered": 40,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.95
        },
        "F07": {
          "n": 76,
          "correct": 56,
          "answered": 76,
          "failed": 0,
          "wrong_valid": 20,
          "accuracy": 0.7368421052631579
        },
        "F08": {
          "n": 67,
          "correct": 61,
          "answered": 67,
          "failed": 0,
          "wrong_valid": 6,
          "accuracy": 0.9104477611940298
        },
        "F09": {
          "n": 71,
          "correct": 51,
          "answered": 71,
          "failed": 0,
          "wrong_valid": 20,
          "accuracy": 0.7183098591549296
        },
        "F10": {
          "n": 74,
          "correct": 38,
          "answered": 74,
          "failed": 0,
          "wrong_valid": 36,
          "accuracy": 0.5135135135135135
        },
        "F11": {
          "n": 41,
          "correct": 37,
          "answered": 41,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.9024390243902439
        },
        "F12": {
          "n": 52,
          "correct": 32,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 20,
          "accuracy": 0.6153846153846154
        },
        "F13": {
          "n": 48,
          "correct": 18,
          "answered": 48,
          "failed": 0,
          "wrong_valid": 30,
          "accuracy": 0.375
        },
        "F14": {
          "n": 42,
          "correct": 40,
          "answered": 42,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9523809523809523
        },
        "F15": {
          "n": 49,
          "correct": 43,
          "answered": 49,
          "failed": 0,
          "wrong_valid": 6,
          "accuracy": 0.8775510204081632
        },
        "F16": {
          "n": 50,
          "correct": 38,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 12,
          "accuracy": 0.76
        },
        "F17": {
          "n": 50,
          "correct": 45,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.9
        },
        "F18": {
          "n": 50,
          "correct": 44,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 6,
          "accuracy": 0.88
        },
        "F19": {
          "n": 58,
          "correct": 57,
          "answered": 58,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9827586206896551
        },
        "F20": {
          "n": 43,
          "correct": 39,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.9069767441860465
        },
        "F21": {
          "n": 43,
          "correct": 41,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9534883720930233
        },
        "F22": {
          "n": 51,
          "correct": 48,
          "answered": 51,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9411764705882353
        },
        "F23": {
          "n": 52,
          "correct": 52,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 0,
          "accuracy": 1.0
        },
        "F24": {
          "n": 43,
          "correct": 42,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9767441860465116
        },
        "F25": {
          "n": 50,
          "correct": 49,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.98
        },
        "F26": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.625
        },
        "F27": {
          "n": 8,
          "correct": 6,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.75
        },
        "F28": {
          "n": 8,
          "correct": 6,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.75
        },
        "F29": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.5
        },
        "F30": {
          "n": 8,
          "correct": 7,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.875
        },
        "F31": {
          "n": 8,
          "correct": 8,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 0,
          "accuracy": 1.0
        }
      },
      "macro_family_accuracy": 0.8454282352448506,
      "new_domains": {
        "n": 48,
        "correct": 36,
        "answered": 48,
        "failed": 0,
        "wrong_valid": 12,
        "accuracy": 0.75
      },
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 1123,
        "answered": 1305,
        "failed": 0,
        "wrong_valid": 182,
        "accuracy": 0.8605363984674329
      },
      "matched_original_1136": {
        "n": 1136,
        "correct": 1014,
        "answered": 1136,
        "failed": 0,
        "wrong_valid": 122,
        "accuracy": 0.8926056338028169
      },
      "added_206": {
        "n": 206,
        "correct": 129,
        "answered": 206,
        "failed": 0,
        "wrong_valid": 77,
        "accuracy": 0.6262135922330098
      },
      "initial_100": {
        "n": 100,
        "correct": 82,
        "answered": 100,
        "failed": 0,
        "wrong_valid": 18,
        "accuracy": 0.82
      },
      "model_id": "reference_sol",
      "label": "GPT-6 Sol \u2014 no reasoning",
      "route": "OpenRouter \u2192 OpenAI, standard service tier",
      "median_ms": 1023.0274999630637,
      "p95_ms": 1546.3492952927484,
      "accuracy_among_usable": 0.8517138599105812,
      "first_statuses": {
        "ok": 1342
      },
      "provider_failures": 0,
      "model_output_failures": 0,
      "cost": {
        "known_usd": 0.8482945,
        "known_decimal": "0.8482945",
        "unknown_attempts": 0,
        "exact_usd": 0.8482945,
        "known_usd_per_1000": 0.6321121460506706,
        "scope": "API-reported USD charge"
      },
      "reasoning_setting": "reasoning.effort=none",
      "reasoning_verification": "Every successful response reports exactly zero reasoning/thinking tokens, with no reasoning content.",
      "compatibility_known_usd": 0.00018,
      "compatibility_unknown_attempts": 0
    },
    "reference_sonnet": {
      "n": 1342,
      "correct": 1070,
      "answered": 1342,
      "failed": 0,
      "wrong_valid": 272,
      "accuracy": 0.797317436661699,
      "eventual": {
        "n": 1342,
        "correct": 1070,
        "answered": 1342,
        "failed": 0,
        "wrong_valid": 272,
        "accuracy": 0.797317436661699
      },
      "latency_first_all": {
        "n": 1342,
        "median_ms": 1505.6673745275475,
        "p95_ms": 2423.8794767647055
      },
      "latency_first_usable": {
        "n": 1342,
        "median_ms": 1505.6673745275475,
        "p95_ms": 2423.8794767647055
      },
      "cost_all_attempts": {
        "known_usd": 1.923908,
        "exact_usd": "1.923908",
        "reported_attempts": 1342,
        "missing_attempts": 0,
        "known_usd_per_1000": 1.4336125186289121
      },
      "cost_first_attempts": {
        "known_usd": 1.923908,
        "exact_usd": "1.923908",
        "reported_attempts": 1342,
        "missing_attempts": 0
      },
      "cost_recovery_attempts": {
        "known_usd": 0.0,
        "exact_usd": "0",
        "reported_attempts": 0,
        "missing_attempts": 0
      },
      "attempts": 1342,
      "recoveries": 0,
      "statuses": {
        "ok": 1342
      },
      "reasoning_token_counts": {
        "0": 1342
      },
      "reasoning_text_responses": 0,
      "reasoning_verification_counts": {
        "explicit_reported_zero": 1342
      },
      "usage": {
        "prompt_tokens": 890684,
        "completion_tokens": 14254,
        "total_tokens": 904938
      },
      "returned_identities": {
        "anthropic/claude-sonnet-5.5": 1342
      },
      "providers": {
        "Anthropic": 1342
      },
      "dates_toronto": {
        "2026-10-19": 1342
      },
      "families": {
        "F01": {
          "n": 43,
          "correct": 42,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9767441860465116
        },
        "F02": {
          "n": 46,
          "correct": 45,
          "answered": 46,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9782608695652174
        },
        "F03": {
          "n": 52,
          "correct": 48,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.9230769230769231
        },
        "F04": {
          "n": 54,
          "correct": 49,
          "answered": 54,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.9074074074074074
        },
        "F05": {
          "n": 49,
          "correct": 45,
          "answered": 49,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.9183673469387755
        },
        "F06": {
          "n": 40,
          "correct": 37,
          "answered": 40,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.925
        },
        "F07": {
          "n": 76,
          "correct": 50,
          "answered": 76,
          "failed": 0,
          "wrong_valid": 26,
          "accuracy": 0.6578947368421053
        },
        "F08": {
          "n": 67,
          "correct": 62,
          "answered": 67,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.9253731343283582
        },
        "F09": {
          "n": 71,
          "correct": 30,
          "answered": 71,
          "failed": 0,
          "wrong_valid": 41,
          "accuracy": 0.4225352112676056
        },
        "F10": {
          "n": 74,
          "correct": 41,
          "answered": 74,
          "failed": 0,
          "wrong_valid": 33,
          "accuracy": 0.5540540540540541
        },
        "F11": {
          "n": 41,
          "correct": 33,
          "answered": 41,
          "failed": 0,
          "wrong_valid": 8,
          "accuracy": 0.8048780487804879
        },
        "F12": {
          "n": 52,
          "correct": 29,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 23,
          "accuracy": 0.5576923076923077
        },
        "F13": {
          "n": 48,
          "correct": 15,
          "answered": 48,
          "failed": 0,
          "wrong_valid": 33,
          "accuracy": 0.3125
        },
        "F14": {
          "n": 42,
          "correct": 38,
          "answered": 42,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.9047619047619048
        },
        "F15": {
          "n": 49,
          "correct": 43,
          "answered": 49,
          "failed": 0,
          "wrong_valid": 6,
          "accuracy": 0.8775510204081632
        },
        "F16": {
          "n": 50,
          "correct": 36,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 14,
          "accuracy": 0.72
        },
        "F17": {
          "n": 50,
          "correct": 45,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.9
        },
        "F18": {
          "n": 50,
          "correct": 41,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 9,
          "accuracy": 0.82
        },
        "F19": {
          "n": 58,
          "correct": 53,
          "answered": 58,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.9137931034482759
        },
        "F20": {
          "n": 43,
          "correct": 36,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 7,
          "accuracy": 0.8372093023255814
        },
        "F21": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9302325581395349
        },
        "F22": {
          "n": 51,
          "correct": 49,
          "answered": 51,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9607843137254902
        },
        "F23": {
          "n": 52,
          "correct": 52,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 0,
          "accuracy": 1.0
        },
        "F24": {
          "n": 43,
          "correct": 39,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.9069767441860465
        },
        "F25": {
          "n": 50,
          "correct": 46,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.92
        },
        "F26": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.625
        },
        "F27": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.5
        },
        "F28": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.5
        },
        "F29": {
          "n": 8,
          "correct": 1,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 7,
          "accuracy": 0.125
        },
        "F30": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.625
        },
        "F31": {
          "n": 8,
          "correct": 7,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.875
        }
      },
      "macro_family_accuracy": 0.7679062313869276,
      "new_domains": {
        "n": 48,
        "correct": 26,
        "answered": 48,
        "failed": 0,
        "wrong_valid": 22,
        "accuracy": 0.5416666666666666
      },
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 1056,
        "answered": 1305,
        "failed": 0,
        "wrong_valid": 249,
        "accuracy": 0.8091954022988506
      },
      "matched_original_1136": {
        "n": 1136,
        "correct": 971,
        "answered": 1136,
        "failed": 0,
        "wrong_valid": 165,
        "accuracy": 0.8547535211267606
      },
      "added_206": {
        "n": 206,
        "correct": 99,
        "answered": 206,
        "failed": 0,
        "wrong_valid": 107,
        "accuracy": 0.48058252427184467
      },
      "initial_100": {
        "n": 100,
        "correct": 80,
        "answered": 100,
        "failed": 0,
        "wrong_valid": 20,
        "accuracy": 0.8
      },
      "model_id": "reference_sonnet",
      "label": "Sonnet 5.5 \u2014 no thinking, JSON-choice",
      "route": "OpenRouter \u2192 Anthropic, standard service",
      "median_ms": 1505.6673745275475,
      "p95_ms": 2423.8794767647055,
      "accuracy_among_usable": 0.797317436661699,
      "first_statuses": {
        "ok": 1342
      },
      "provider_failures": 0,
      "model_output_failures": 0,
      "cost": {
        "known_usd": 1.923908,
        "known_decimal": "1.923908",
        "unknown_attempts": 0,
        "exact_usd": 1.923908,
        "known_usd_per_1000": 1.4336125186289121,
        "scope": "API-reported USD charge"
      },
      "reasoning_setting": "thinking.type=between_tools; effort=high; no tools",
      "reasoning_verification": "Every successful response reports exactly zero reasoning/thinking tokens, with no reasoning content.",
      "compatibility_known_usd": 0.002182,
      "compatibility_unknown_attempts": 0
    },
    "reference_qwen": {
      "n": 1342,
      "correct": 967,
      "answered": 1317,
      "failed": 25,
      "wrong_valid": 350,
      "accuracy": 0.7205663189269746,
      "eventual": {
        "n": 1342,
        "correct": 971,
        "answered": 1322,
        "failed": 20,
        "wrong_valid": 351,
        "accuracy": 0.7235469448584203
      },
      "latency_first_all": {
        "n": 1342,
        "median_ms": 1190.6628959695809,
        "p95_ms": 1731.1974538024515
      },
      "latency_first_usable": {
        "n": 1317,
        "median_ms": 1194.47400001809,
        "p95_ms": 1735.4193163570026
      },
      "cost_all_attempts": {
        "known_usd": 0.82509,
        "exact_usd": "0.82509000000000002271",
        "reported_attempts": 1322,
        "missing_attempts": 43,
        "known_usd_per_1000": 0.6148211624441132
      },
      "cost_first_attempts": {
        "known_usd": 0.822154,
        "exact_usd": "0.82215400000000002274",
        "reported_attempts": 1317,
        "missing_attempts": 25
      },
      "cost_recovery_attempts": {
        "known_usd": 0.002936,
        "exact_usd": "0.00293599999999999997",
        "reported_attempts": 5,
        "missing_attempts": 18
      },
      "attempts": 1365,
      "recoveries": 23,
      "statuses": {
        "ok": 1317,
        "transport_failure": 1,
        "http_failure": 24
      },
      "reasoning_token_counts": {
        "None": 1342
      },
      "reasoning_text_responses": 0,
      "reasoning_verification_counts": {
        "requested_none_catalog_supported_no_token_telemetry": 1342
      },
      "hypercredits_all_attempts": {
        "known": 16.5018,
        "missing_attempts": 43,
        "scope": "Provider-reported quota debit, not a cash invoice"
      },
      "usage": {
        "prompt_tokens": 408579,
        "completion_tokens": 1322,
        "total_tokens": 409901
      },
      "returned_identities": {
        "qwen3.8-max": 1322,
        "unreported": 43
      },
      "providers": {
        "Hyper Charm (request host)": 1365
      },
      "dates_toronto": {
        "2026-10-19": 1342
      },
      "families": {
        "F01": {
          "n": 43,
          "correct": 37,
          "answered": 40,
          "failed": 3,
          "wrong_valid": 3,
          "accuracy": 0.8604651162790697
        },
        "F02": {
          "n": 46,
          "correct": 38,
          "answered": 46,
          "failed": 0,
          "wrong_valid": 8,
          "accuracy": 0.8260869565217391
        },
        "F03": {
          "n": 52,
          "correct": 44,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 8,
          "accuracy": 0.8461538461538461
        },
        "F04": {
          "n": 54,
          "correct": 45,
          "answered": 54,
          "failed": 0,
          "wrong_valid": 9,
          "accuracy": 0.8333333333333334
        },
        "F05": {
          "n": 49,
          "correct": 44,
          "answered": 48,
          "failed": 1,
          "wrong_valid": 4,
          "accuracy": 0.8979591836734694
        },
        "F06": {
          "n": 40,
          "correct": 40,
          "answered": 40,
          "failed": 0,
          "wrong_valid": 0,
          "accuracy": 1.0
        },
        "F07": {
          "n": 76,
          "correct": 42,
          "answered": 74,
          "failed": 2,
          "wrong_valid": 32,
          "accuracy": 0.5526315789473685
        },
        "F08": {
          "n": 67,
          "correct": 58,
          "answered": 67,
          "failed": 0,
          "wrong_valid": 9,
          "accuracy": 0.8656716417910447
        },
        "F09": {
          "n": 71,
          "correct": 24,
          "answered": 70,
          "failed": 1,
          "wrong_valid": 46,
          "accuracy": 0.3380281690140845
        },
        "F10": {
          "n": 74,
          "correct": 30,
          "answered": 70,
          "failed": 4,
          "wrong_valid": 40,
          "accuracy": 0.40540540540540543
        },
        "F11": {
          "n": 41,
          "correct": 25,
          "answered": 38,
          "failed": 3,
          "wrong_valid": 13,
          "accuracy": 0.6097560975609756
        },
        "F12": {
          "n": 52,
          "correct": 27,
          "answered": 51,
          "failed": 1,
          "wrong_valid": 24,
          "accuracy": 0.5192307692307693
        },
        "F13": {
          "n": 48,
          "correct": 11,
          "answered": 47,
          "failed": 1,
          "wrong_valid": 36,
          "accuracy": 0.22916666666666666
        },
        "F14": {
          "n": 42,
          "correct": 34,
          "answered": 42,
          "failed": 0,
          "wrong_valid": 8,
          "accuracy": 0.8095238095238095
        },
        "F15": {
          "n": 49,
          "correct": 28,
          "answered": 47,
          "failed": 2,
          "wrong_valid": 19,
          "accuracy": 0.5714285714285714
        },
        "F16": {
          "n": 50,
          "correct": 30,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 20,
          "accuracy": 0.6
        },
        "F17": {
          "n": 50,
          "correct": 38,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 12,
          "accuracy": 0.76
        },
        "F18": {
          "n": 50,
          "correct": 36,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 14,
          "accuracy": 0.72
        },
        "F19": {
          "n": 58,
          "correct": 53,
          "answered": 57,
          "failed": 1,
          "wrong_valid": 4,
          "accuracy": 0.9137931034482759
        },
        "F20": {
          "n": 43,
          "correct": 35,
          "answered": 42,
          "failed": 1,
          "wrong_valid": 7,
          "accuracy": 0.813953488372093
        },
        "F21": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9302325581395349
        },
        "F22": {
          "n": 51,
          "correct": 47,
          "answered": 50,
          "failed": 1,
          "wrong_valid": 3,
          "accuracy": 0.9215686274509803
        },
        "F23": {
          "n": 52,
          "correct": 49,
          "answered": 51,
          "failed": 1,
          "wrong_valid": 2,
          "accuracy": 0.9423076923076923
        },
        "F24": {
          "n": 43,
          "correct": 38,
          "answered": 41,
          "failed": 2,
          "wrong_valid": 3,
          "accuracy": 0.8837209302325582
        },
        "F25": {
          "n": 50,
          "correct": 46,
          "answered": 49,
          "failed": 1,
          "wrong_valid": 3,
          "accuracy": 0.92
        },
        "F26": {
          "n": 8,
          "correct": 6,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.75
        },
        "F27": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.5
        },
        "F28": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.5
        },
        "F29": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.375
        },
        "F30": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.5
        },
        "F31": {
          "n": 8,
          "correct": 7,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.875
        }
      },
      "macro_family_accuracy": 0.7119489530800417,
      "new_domains": {
        "n": 48,
        "correct": 28,
        "answered": 48,
        "failed": 0,
        "wrong_valid": 20,
        "accuracy": 0.5833333333333334
      },
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 948,
        "answered": 1281,
        "failed": 24,
        "wrong_valid": 333,
        "accuracy": 0.7264367816091954
      },
      "matched_original_1136": {
        "n": 1136,
        "correct": 855,
        "answered": 1113,
        "failed": 23,
        "wrong_valid": 258,
        "accuracy": 0.7526408450704225
      },
      "added_206": {
        "n": 206,
        "correct": 112,
        "answered": 204,
        "failed": 2,
        "wrong_valid": 92,
        "accuracy": 0.5436893203883495
      },
      "initial_100": {
        "n": 100,
        "correct": 70,
        "answered": 100,
        "failed": 0,
        "wrong_valid": 30,
        "accuracy": 0.7
      },
      "model_id": "reference_qwen",
      "label": "Qwen3.8-Max \u2014 none, Hyper Charm",
      "route": "Hyper Charm direct, sequential capacity1",
      "median_ms": 1190.6628959695809,
      "p95_ms": 1731.1974538024515,
      "accuracy_among_usable": 0.7342444950645406,
      "first_statuses": {
        "ok": 1317,
        "transport_failure": 1,
        "http_failure": 24
      },
      "provider_failures": 25,
      "model_output_failures": 0,
      "cost": {
        "known_usd": 0.82509,
        "known_decimal": "0.82509000000000002271",
        "unknown_attempts": 43,
        "exact_usd": null,
        "known_usd_per_1000": 0.6148211624441132,
        "scope": "USD-equivalent prepaid quota valuation, not cash invoice"
      },
      "reasoning_setting": "reasoning_effort=none, documented/catalog-supported",
      "reasoning_verification": "Provider omits reasoning-token telemetry. The none setting is catalog-supported and requested explicitly; no reasoning text is allowed. Unknown token counts are not treated as verified zeros.",
      "compatibility_known_usd": 0.001112,
      "compatibility_unknown_attempts": 0
    },
    "d3_turbo": {
      "model_id": "d3_turbo",
      "label": "d3-turbo",
      "n": 1342,
      "correct": 1106,
      "answered": 1342,
      "wrong_valid": 236,
      "failed": 0,
      "accuracy": 0.8241430700447094,
      "accuracy_among_usable": 0.8241430700447094,
      "mean_response_ms": 181.9034249486399,
      "median_ms": 165.2547080302611,
      "p95_ms": 297.8397538594437,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "provider_failures": 0,
      "model_output_failures": 0,
      "probability_warnings": 0,
      "eventual": {
        "n": 1342,
        "correct": 1106,
        "answered": 1342,
        "failed": 0,
        "wrong_valid": 236,
        "accuracy": 0.8241430700447094
      },
      "cost": {
        "known_usd": null,
        "known_decimal": null,
        "known_usd_per_1000": null,
        "unknown_attempts": 1342,
        "exact_usd": null,
        "public_free_access": true,
        "accounted_access_cost_usd": 0.0,
        "scope": "Currently free public endpoint; no API-reported monetary charge and no production-price guarantee"
      },
      "families": {
        "F01": {
          "n": 43,
          "correct": 41,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9534883720930233
        },
        "F02": {
          "n": 46,
          "correct": 46,
          "answered": 46,
          "failed": 0,
          "wrong_valid": 0,
          "accuracy": 1.0
        },
        "F03": {
          "n": 52,
          "correct": 51,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9807692307692307
        },
        "F04": {
          "n": 54,
          "correct": 50,
          "answered": 54,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.9259259259259259
        },
        "F05": {
          "n": 49,
          "correct": 45,
          "answered": 49,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.9183673469387755
        },
        "F06": {
          "n": 40,
          "correct": 38,
          "answered": 40,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.95
        },
        "F07": {
          "n": 76,
          "correct": 54,
          "answered": 76,
          "failed": 0,
          "wrong_valid": 22,
          "accuracy": 0.7105263157894737
        },
        "F08": {
          "n": 67,
          "correct": 63,
          "answered": 67,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.9402985074626866
        },
        "F09": {
          "n": 71,
          "correct": 35,
          "answered": 71,
          "failed": 0,
          "wrong_valid": 36,
          "accuracy": 0.49295774647887325
        },
        "F10": {
          "n": 74,
          "correct": 49,
          "answered": 74,
          "failed": 0,
          "wrong_valid": 25,
          "accuracy": 0.6621621621621622
        },
        "F11": {
          "n": 41,
          "correct": 35,
          "answered": 41,
          "failed": 0,
          "wrong_valid": 6,
          "accuracy": 0.8536585365853658
        },
        "F12": {
          "n": 52,
          "correct": 31,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 21,
          "accuracy": 0.5961538461538461
        },
        "F13": {
          "n": 48,
          "correct": 20,
          "answered": 48,
          "failed": 0,
          "wrong_valid": 28,
          "accuracy": 0.4166666666666667
        },
        "F14": {
          "n": 42,
          "correct": 41,
          "answered": 42,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9761904761904762
        },
        "F15": {
          "n": 49,
          "correct": 36,
          "answered": 49,
          "failed": 0,
          "wrong_valid": 13,
          "accuracy": 0.7346938775510204
        },
        "F16": {
          "n": 50,
          "correct": 34,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 16,
          "accuracy": 0.68
        },
        "F17": {
          "n": 50,
          "correct": 47,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.94
        },
        "F18": {
          "n": 50,
          "correct": 38,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 12,
          "accuracy": 0.76
        },
        "F19": {
          "n": 58,
          "correct": 56,
          "answered": 58,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9655172413793104
        },
        "F20": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.8837209302325582
        },
        "F21": {
          "n": 43,
          "correct": 41,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9534883720930233
        },
        "F22": {
          "n": 51,
          "correct": 48,
          "answered": 51,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9411764705882353
        },
        "F23": {
          "n": 52,
          "correct": 52,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 0,
          "accuracy": 1.0
        },
        "F24": {
          "n": 43,
          "correct": 42,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9767441860465116
        },
        "F25": {
          "n": 50,
          "correct": 48,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.96
        },
        "F26": {
          "n": 8,
          "correct": 6,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.75
        },
        "F27": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.5
        },
        "F28": {
          "n": 8,
          "correct": 2,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 6,
          "accuracy": 0.25
        },
        "F29": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.625
        },
        "F30": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.5
        },
        "F31": {
          "n": 8,
          "correct": 6,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.75
        }
      },
      "dates_toronto": {
        "2026-10-20": 1342
      },
      "returned_identities": {
        "vllm-sr/d3-turbo": 1342
      },
      "providers": {
        "direct": 1342
      },
      "route": "Direct \u2192 https://decision.vllm-sr.ai/v1/systemone \u2192 vllm-sr/d3-turbo",
      "output_token_values": {
        "0": 1342
      },
      "input_tokens": 480427,
      "macro_family_accuracy": 0.7918550390679729,
      "new_domains": {
        "n": 48,
        "correct": 27,
        "answered": 48,
        "failed": 0,
        "wrong_valid": 21,
        "accuracy": 0.5625
      },
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 1092,
        "answered": 1305,
        "failed": 0,
        "wrong_valid": 213,
        "accuracy": 0.8367816091954023
      },
      "compatibility": {
        "status": "ok",
        "accounted_cost_usd": 0.0,
        "reported_cost_usd": null,
        "cost_source": "public_free_endpoint_not_api_reported"
      }
    },
    "amos_large": {
      "model_id": "amos_large",
      "label": "Amos 1 Large",
      "n": 1342,
      "correct": 1074,
      "answered": 1342,
      "wrong_valid": 268,
      "failed": 0,
      "accuracy": 0.8002980625931445,
      "accuracy_among_usable": 0.8002980625931445,
      "mean_response_ms": 306.1684600538026,
      "median_ms": 310.6975415139459,
      "p95_ms": 359.8499482031912,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "provider_failures": 0,
      "model_output_failures": 0,
      "probability_warnings": 0,
      "eventual": {
        "n": 1342,
        "correct": 1074,
        "answered": 1342,
        "failed": 0,
        "wrong_valid": 268,
        "accuracy": 0.8002980625931445
      },
      "cost": {
        "known_usd": null,
        "known_decimal": null,
        "known_usd_per_1000": null,
        "unknown_attempts": 1342,
        "exact_usd": null,
        "public_free_access": true,
        "accounted_access_cost_usd": 0.0,
        "scope": "Currently free public endpoint; no API-reported monetary charge and no production-price guarantee"
      },
      "families": {
        "F01": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9302325581395349
        },
        "F02": {
          "n": 46,
          "correct": 44,
          "answered": 46,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9565217391304348
        },
        "F03": {
          "n": 52,
          "correct": 49,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9423076923076923
        },
        "F04": {
          "n": 54,
          "correct": 51,
          "answered": 54,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9444444444444444
        },
        "F05": {
          "n": 49,
          "correct": 45,
          "answered": 49,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.9183673469387755
        },
        "F06": {
          "n": 40,
          "correct": 38,
          "answered": 40,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.95
        },
        "F07": {
          "n": 76,
          "correct": 54,
          "answered": 76,
          "failed": 0,
          "wrong_valid": 22,
          "accuracy": 0.7105263157894737
        },
        "F08": {
          "n": 67,
          "correct": 62,
          "answered": 67,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.9253731343283582
        },
        "F09": {
          "n": 71,
          "correct": 37,
          "answered": 71,
          "failed": 0,
          "wrong_valid": 34,
          "accuracy": 0.5211267605633803
        },
        "F10": {
          "n": 74,
          "correct": 51,
          "answered": 74,
          "failed": 0,
          "wrong_valid": 23,
          "accuracy": 0.6891891891891891
        },
        "F11": {
          "n": 41,
          "correct": 35,
          "answered": 41,
          "failed": 0,
          "wrong_valid": 6,
          "accuracy": 0.8536585365853658
        },
        "F12": {
          "n": 52,
          "correct": 26,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 26,
          "accuracy": 0.5
        },
        "F13": {
          "n": 48,
          "correct": 16,
          "answered": 48,
          "failed": 0,
          "wrong_valid": 32,
          "accuracy": 0.3333333333333333
        },
        "F14": {
          "n": 42,
          "correct": 41,
          "answered": 42,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9761904761904762
        },
        "F15": {
          "n": 49,
          "correct": 36,
          "answered": 49,
          "failed": 0,
          "wrong_valid": 13,
          "accuracy": 0.7346938775510204
        },
        "F16": {
          "n": 50,
          "correct": 30,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 20,
          "accuracy": 0.6
        },
        "F17": {
          "n": 50,
          "correct": 46,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.92
        },
        "F18": {
          "n": 50,
          "correct": 36,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 14,
          "accuracy": 0.72
        },
        "F19": {
          "n": 58,
          "correct": 55,
          "answered": 58,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9482758620689655
        },
        "F20": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.8837209302325582
        },
        "F21": {
          "n": 43,
          "correct": 41,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9534883720930233
        },
        "F22": {
          "n": 51,
          "correct": 47,
          "answered": 51,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.9215686274509803
        },
        "F23": {
          "n": 52,
          "correct": 50,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9615384615384616
        },
        "F24": {
          "n": 43,
          "correct": 41,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9534883720930233
        },
        "F25": {
          "n": 50,
          "correct": 44,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 6,
          "accuracy": 0.88
        },
        "F26": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.375
        },
        "F27": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.375
        },
        "F28": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.375
        },
        "F29": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.375
        },
        "F30": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.375
        },
        "F31": {
          "n": 8,
          "correct": 6,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.75
        }
      },
      "dates_toronto": {
        "2026-10-20": 1342
      },
      "returned_identities": {
        "amos-1-large": 1342
      },
      "providers": {
        "direct": 1342
      },
      "route": "Direct \u2192 https://api.amos.scira.ai/v1/systemone \u2192 amos-1-large",
      "output_token_values": {
        "0": 1342
      },
      "input_tokens": 465665,
      "macro_family_accuracy": 0.7500982590312416,
      "new_domains": {
        "n": 48,
        "correct": 21,
        "answered": 48,
        "failed": 0,
        "wrong_valid": 27,
        "accuracy": 0.4375
      },
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 1059,
        "answered": 1305,
        "failed": 0,
        "wrong_valid": 246,
        "accuracy": 0.8114942528735632
      },
      "compatibility": {
        "status": "ok",
        "accounted_cost_usd": 0.0,
        "reported_cost_usd": null,
        "cost_source": "public_free_endpoint_not_api_reported"
      }
    },
    "kettei_fat": {
      "model_id": "kettei_fat",
      "label": "kettei-fat",
      "n": 1342,
      "correct": 1066,
      "answered": 1342,
      "wrong_valid": 276,
      "failed": 0,
      "accuracy": 0.7943368107302533,
      "accuracy_among_usable": 0.7943368107302533,
      "mean_response_ms": 179.42590906099804,
      "median_ms": 173.85120794642717,
      "p95_ms": 213.5956204903778,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "provider_failures": 0,
      "model_output_failures": 0,
      "probability_warnings": 0,
      "eventual": {
        "n": 1342,
        "correct": 1066,
        "answered": 1342,
        "failed": 0,
        "wrong_valid": 276,
        "accuracy": 0.7943368107302533
      },
      "cost": {
        "known_usd": 0.02071056,
        "known_decimal": "0.02071056",
        "known_usd_per_1000": 0.015432608047690016,
        "unknown_attempts": 0,
        "exact_usd": 0.02071056,
        "public_free_access": false,
        "accounted_access_cost_usd": 0.02071056,
        "scope": "API-reported USD charges; starter credit is payment credit, not a zero price"
      },
      "families": {
        "F01": {
          "n": 43,
          "correct": 41,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9534883720930233
        },
        "F02": {
          "n": 46,
          "correct": 46,
          "answered": 46,
          "failed": 0,
          "wrong_valid": 0,
          "accuracy": 1.0
        },
        "F03": {
          "n": 52,
          "correct": 50,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9615384615384616
        },
        "F04": {
          "n": 54,
          "correct": 50,
          "answered": 54,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.9259259259259259
        },
        "F05": {
          "n": 49,
          "correct": 47,
          "answered": 49,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9591836734693877
        },
        "F06": {
          "n": 40,
          "correct": 39,
          "answered": 40,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.975
        },
        "F07": {
          "n": 76,
          "correct": 44,
          "answered": 76,
          "failed": 0,
          "wrong_valid": 32,
          "accuracy": 0.5789473684210527
        },
        "F08": {
          "n": 67,
          "correct": 53,
          "answered": 67,
          "failed": 0,
          "wrong_valid": 14,
          "accuracy": 0.7910447761194029
        },
        "F09": {
          "n": 71,
          "correct": 19,
          "answered": 71,
          "failed": 0,
          "wrong_valid": 52,
          "accuracy": 0.2676056338028169
        },
        "F10": {
          "n": 74,
          "correct": 43,
          "answered": 74,
          "failed": 0,
          "wrong_valid": 31,
          "accuracy": 0.581081081081081
        },
        "F11": {
          "n": 41,
          "correct": 36,
          "answered": 41,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.8780487804878049
        },
        "F12": {
          "n": 52,
          "correct": 29,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 23,
          "accuracy": 0.5576923076923077
        },
        "F13": {
          "n": 48,
          "correct": 16,
          "answered": 48,
          "failed": 0,
          "wrong_valid": 32,
          "accuracy": 0.3333333333333333
        },
        "F14": {
          "n": 42,
          "correct": 39,
          "answered": 42,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9285714285714286
        },
        "F15": {
          "n": 49,
          "correct": 38,
          "answered": 49,
          "failed": 0,
          "wrong_valid": 11,
          "accuracy": 0.7755102040816326
        },
        "F16": {
          "n": 50,
          "correct": 37,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 13,
          "accuracy": 0.74
        },
        "F17": {
          "n": 50,
          "correct": 43,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 7,
          "accuracy": 0.86
        },
        "F18": {
          "n": 50,
          "correct": 45,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.9
        },
        "F19": {
          "n": 58,
          "correct": 56,
          "answered": 58,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9655172413793104
        },
        "F20": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.8837209302325582
        },
        "F21": {
          "n": 43,
          "correct": 42,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9767441860465116
        },
        "F22": {
          "n": 51,
          "correct": 48,
          "answered": 51,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9411764705882353
        },
        "F23": {
          "n": 52,
          "correct": 51,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9807692307692307
        },
        "F24": {
          "n": 43,
          "correct": 43,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 0,
          "accuracy": 1.0
        },
        "F25": {
          "n": 50,
          "correct": 46,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.92
        },
        "F26": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.5
        },
        "F27": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.5
        },
        "F28": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.375
        },
        "F29": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.625
        },
        "F30": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.625
        },
        "F31": {
          "n": 8,
          "correct": 6,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.75
        }
      },
      "dates_toronto": {
        "2026-10-20": 1342
      },
      "returned_identities": {
        "kettei-fat": 1342
      },
      "providers": {
        "direct": 1342
      },
      "route": "Direct \u2192 https://api.sqwish.ai/v1/systemone \u2192 kettei-fat",
      "output_token_values": {
        "0": 1342
      },
      "input_tokens": 345176,
      "macro_family_accuracy": 0.7745128840526937,
      "new_domains": {
        "n": 48,
        "correct": 27,
        "answered": 48,
        "failed": 0,
        "wrong_valid": 21,
        "accuracy": 0.5625
      },
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 1049,
        "answered": 1305,
        "failed": 0,
        "wrong_valid": 256,
        "accuracy": 0.803831417624521
      },
      "compatibility": {
        "status": "ok",
        "accounted_cost_usd": 1.92e-06,
        "reported_cost_usd": 1.92e-06,
        "cost_source": "api_reported_charge"
      }
    },
    "mammoth1": {
      "model_id": "mammoth1",
      "label": "Mammoth-1",
      "n": 1342,
      "correct": 1139,
      "answered": 1342,
      "wrong_valid": 203,
      "failed": 0,
      "accuracy": 0.8487332339791356,
      "accuracy_among_usable": 0.8487332339791356,
      "mean_response_ms": 301.3734981484365,
      "median_ms": 239.56312499649357,
      "p95_ms": 665.6302211500588,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "provider_failures": 0,
      "model_output_failures": 0,
      "probability_warnings": 0,
      "eventual": {
        "n": 1342,
        "correct": 1139,
        "answered": 1342,
        "failed": 0,
        "wrong_valid": 203,
        "accuracy": 0.8487332339791356
      },
      "cost": {
        "known_usd": null,
        "known_decimal": null,
        "known_usd_per_1000": null,
        "unknown_attempts": 1342,
        "exact_usd": null,
        "public_free_access": true,
        "accounted_access_cost_usd": 0.0,
        "scope": "Captured promotional free access; no monetary receipts, not a permanent production price"
      },
      "families": {
        "F01": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9302325581395349
        },
        "F02": {
          "n": 46,
          "correct": 45,
          "answered": 46,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9782608695652174
        },
        "F03": {
          "n": 52,
          "correct": 50,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9615384615384616
        },
        "F04": {
          "n": 54,
          "correct": 51,
          "answered": 54,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9444444444444444
        },
        "F05": {
          "n": 49,
          "correct": 43,
          "answered": 49,
          "failed": 0,
          "wrong_valid": 6,
          "accuracy": 0.8775510204081632
        },
        "F06": {
          "n": 40,
          "correct": 39,
          "answered": 40,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.975
        },
        "F07": {
          "n": 76,
          "correct": 59,
          "answered": 76,
          "failed": 0,
          "wrong_valid": 17,
          "accuracy": 0.7763157894736842
        },
        "F08": {
          "n": 67,
          "correct": 64,
          "answered": 67,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9552238805970149
        },
        "F09": {
          "n": 71,
          "correct": 44,
          "answered": 71,
          "failed": 0,
          "wrong_valid": 27,
          "accuracy": 0.6197183098591549
        },
        "F10": {
          "n": 74,
          "correct": 48,
          "answered": 74,
          "failed": 0,
          "wrong_valid": 26,
          "accuracy": 0.6486486486486487
        },
        "F11": {
          "n": 41,
          "correct": 38,
          "answered": 41,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.926829268292683
        },
        "F12": {
          "n": 52,
          "correct": 38,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 14,
          "accuracy": 0.7307692307692307
        },
        "F13": {
          "n": 48,
          "correct": 18,
          "answered": 48,
          "failed": 0,
          "wrong_valid": 30,
          "accuracy": 0.375
        },
        "F14": {
          "n": 42,
          "correct": 40,
          "answered": 42,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9523809523809523
        },
        "F15": {
          "n": 49,
          "correct": 38,
          "answered": 49,
          "failed": 0,
          "wrong_valid": 11,
          "accuracy": 0.7755102040816326
        },
        "F16": {
          "n": 50,
          "correct": 37,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 13,
          "accuracy": 0.74
        },
        "F17": {
          "n": 50,
          "correct": 47,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.94
        },
        "F18": {
          "n": 50,
          "correct": 44,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 6,
          "accuracy": 0.88
        },
        "F19": {
          "n": 58,
          "correct": 57,
          "answered": 58,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9827586206896551
        },
        "F20": {
          "n": 43,
          "correct": 39,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.9069767441860465
        },
        "F21": {
          "n": 43,
          "correct": 41,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9534883720930233
        },
        "F22": {
          "n": 51,
          "correct": 48,
          "answered": 51,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9411764705882353
        },
        "F23": {
          "n": 52,
          "correct": 52,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 0,
          "accuracy": 1.0
        },
        "F24": {
          "n": 43,
          "correct": 42,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9767441860465116
        },
        "F25": {
          "n": 50,
          "correct": 47,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.94
        },
        "F26": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.625
        },
        "F27": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.5
        },
        "F28": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.5
        },
        "F29": {
          "n": 8,
          "correct": 6,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.75
        },
        "F30": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.625
        },
        "F31": {
          "n": 8,
          "correct": 6,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.75
        }
      },
      "dates_toronto": {
        "2026-10-21": 1342
      },
      "returned_identities": {
        "decision-models/baseten-mammoth-27b-latest": 1342
      },
      "providers": {
        "Baseten direct": 1342
      },
      "route": "Direct \u2192 Baseten \u2192 decision-models/baseten-mammoth-27b-latest",
      "output_token_values": {
        "1": 1342
      },
      "input_tokens": 484453,
      "macro_family_accuracy": 0.8205989687678159,
      "new_domains": {
        "n": 48,
        "correct": 30,
        "answered": 48,
        "failed": 0,
        "wrong_valid": 18,
        "accuracy": 0.625
      },
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 1128,
        "answered": 1305,
        "failed": 0,
        "wrong_valid": 177,
        "accuracy": 0.864367816091954
      },
      "original_1136": {
        "n": 1136,
        "correct": 1019,
        "answered": 1136,
        "failed": 0,
        "wrong_valid": 117,
        "accuracy": 0.8970070422535211
      },
      "added_206": {
        "n": 206,
        "correct": 120,
        "answered": 206,
        "failed": 0,
        "wrong_valid": 86,
        "accuracy": 0.5825242718446602
      },
      "compatibility": {
        "status": "ok",
        "reported_cost_usd": null,
        "accounted_cost_usd": 0.0,
        "cost_source": "captured_promotional_zero_tariff_not_receipt"
      }
    },
    "elephant1": {
      "model_id": "elephant1",
      "label": "Elephant-1",
      "n": 1342,
      "correct": 1004,
      "answered": 1342,
      "wrong_valid": 338,
      "failed": 0,
      "accuracy": 0.7481371087928465,
      "accuracy_among_usable": 0.7481371087928465,
      "mean_response_ms": 163.87187118225037,
      "median_ms": 139.16606250131736,
      "p95_ms": 271.94698334860743,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "provider_failures": 0,
      "model_output_failures": 0,
      "probability_warnings": 0,
      "eventual": {
        "n": 1342,
        "correct": 1004,
        "answered": 1342,
        "failed": 0,
        "wrong_valid": 338,
        "accuracy": 0.7481371087928465
      },
      "cost": {
        "known_usd": null,
        "known_decimal": null,
        "known_usd_per_1000": null,
        "unknown_attempts": 1342,
        "exact_usd": null,
        "public_free_access": true,
        "accounted_access_cost_usd": 0.0,
        "scope": "Captured promotional free access; no monetary receipts, not a permanent production price"
      },
      "families": {
        "F01": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9302325581395349
        },
        "F02": {
          "n": 46,
          "correct": 44,
          "answered": 46,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9565217391304348
        },
        "F03": {
          "n": 52,
          "correct": 38,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 14,
          "accuracy": 0.7307692307692307
        },
        "F04": {
          "n": 54,
          "correct": 48,
          "answered": 54,
          "failed": 0,
          "wrong_valid": 6,
          "accuracy": 0.8888888888888888
        },
        "F05": {
          "n": 49,
          "correct": 44,
          "answered": 49,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.8979591836734694
        },
        "F06": {
          "n": 40,
          "correct": 40,
          "answered": 40,
          "failed": 0,
          "wrong_valid": 0,
          "accuracy": 1.0
        },
        "F07": {
          "n": 76,
          "correct": 49,
          "answered": 76,
          "failed": 0,
          "wrong_valid": 27,
          "accuracy": 0.6447368421052632
        },
        "F08": {
          "n": 67,
          "correct": 60,
          "answered": 67,
          "failed": 0,
          "wrong_valid": 7,
          "accuracy": 0.8955223880597015
        },
        "F09": {
          "n": 71,
          "correct": 33,
          "answered": 71,
          "failed": 0,
          "wrong_valid": 38,
          "accuracy": 0.4647887323943662
        },
        "F10": {
          "n": 74,
          "correct": 43,
          "answered": 74,
          "failed": 0,
          "wrong_valid": 31,
          "accuracy": 0.581081081081081
        },
        "F11": {
          "n": 41,
          "correct": 30,
          "answered": 41,
          "failed": 0,
          "wrong_valid": 11,
          "accuracy": 0.7317073170731707
        },
        "F12": {
          "n": 52,
          "correct": 28,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 24,
          "accuracy": 0.5384615384615384
        },
        "F13": {
          "n": 48,
          "correct": 12,
          "answered": 48,
          "failed": 0,
          "wrong_valid": 36,
          "accuracy": 0.25
        },
        "F14": {
          "n": 42,
          "correct": 25,
          "answered": 42,
          "failed": 0,
          "wrong_valid": 17,
          "accuracy": 0.5952380952380952
        },
        "F15": {
          "n": 49,
          "correct": 29,
          "answered": 49,
          "failed": 0,
          "wrong_valid": 20,
          "accuracy": 0.5918367346938775
        },
        "F16": {
          "n": 50,
          "correct": 25,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 25,
          "accuracy": 0.5
        },
        "F17": {
          "n": 50,
          "correct": 46,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.92
        },
        "F18": {
          "n": 50,
          "correct": 34,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 16,
          "accuracy": 0.68
        },
        "F19": {
          "n": 58,
          "correct": 54,
          "answered": 58,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.9310344827586207
        },
        "F20": {
          "n": 43,
          "correct": 38,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.8837209302325582
        },
        "F21": {
          "n": 43,
          "correct": 41,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9534883720930233
        },
        "F22": {
          "n": 51,
          "correct": 46,
          "answered": 51,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.9019607843137255
        },
        "F23": {
          "n": 52,
          "correct": 50,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9615384615384616
        },
        "F24": {
          "n": 43,
          "correct": 40,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9302325581395349
        },
        "F25": {
          "n": 50,
          "correct": 45,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.9
        },
        "F26": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.375
        },
        "F27": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.5
        },
        "F28": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.375
        },
        "F29": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.375
        },
        "F30": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.5
        },
        "F31": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.625
        }
      },
      "dates_toronto": {
        "2026-10-21": 1342
      },
      "returned_identities": {
        "decision-models/baseten-elephant-9b-latest": 1342
      },
      "providers": {
        "Baseten direct": 1342
      },
      "route": "Direct \u2192 Baseten \u2192 decision-models/baseten-elephant-9b-latest",
      "output_token_values": {
        "1": 1342
      },
      "input_tokens": 484453,
      "macro_family_accuracy": 0.7099909651220829,
      "new_domains": {
        "n": 48,
        "correct": 22,
        "answered": 48,
        "failed": 0,
        "wrong_valid": 26,
        "accuracy": 0.4583333333333333
      },
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 990,
        "answered": 1305,
        "failed": 0,
        "wrong_valid": 315,
        "accuracy": 0.7586206896551724
      },
      "original_1136": {
        "n": 1136,
        "correct": 902,
        "answered": 1136,
        "failed": 0,
        "wrong_valid": 234,
        "accuracy": 0.7940140845070423
      },
      "added_206": {
        "n": 206,
        "correct": 102,
        "answered": 206,
        "failed": 0,
        "wrong_valid": 104,
        "accuracy": 0.49514563106796117
      },
      "compatibility": {
        "status": "ok",
        "reported_cost_usd": null,
        "accounted_cost_usd": 0.0,
        "cost_source": "captured_promotional_zero_tariff_not_receipt"
      }
    },
    "drex_max": {
      "model_id": "drex_max",
      "label": "Drex Max",
      "n": 1342,
      "correct": 1127,
      "answered": 1342,
      "wrong_valid": 215,
      "failed": 0,
      "accuracy": 0.8397913561847988,
      "accuracy_among_usable": 0.8397913561847988,
      "mean_response_ms": 289.75990623420995,
      "median_ms": 285.8057909979834,
      "p95_ms": 444.8038062444539,
      "attempts": 1342,
      "recoveries": 0,
      "first_statuses": {
        "ok": 1342
      },
      "provider_failures": 0,
      "model_output_failures": 0,
      "probability_warnings": 0,
      "eventual": {
        "n": 1342,
        "correct": 1127,
        "answered": 1342,
        "failed": 0,
        "wrong_valid": 215,
        "accuracy": 0.8397913561847988
      },
      "cost": {
        "known_usd": 0.02842302,
        "known_decimal": "0.02842302",
        "known_usd_per_1000": 0.021179597615499254,
        "unknown_attempts": 0,
        "exact_usd": 0.02842302,
        "public_free_access": false,
        "accounted_access_cost_usd": 0.02842302,
        "scope": "API-reported OpenRouter charges, all attempts"
      },
      "families": {
        "F01": {
          "n": 43,
          "correct": 41,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9534883720930233
        },
        "F02": {
          "n": 46,
          "correct": 45,
          "answered": 46,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9782608695652174
        },
        "F03": {
          "n": 52,
          "correct": 50,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9615384615384616
        },
        "F04": {
          "n": 54,
          "correct": 51,
          "answered": 54,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9444444444444444
        },
        "F05": {
          "n": 49,
          "correct": 46,
          "answered": 49,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9387755102040817
        },
        "F06": {
          "n": 40,
          "correct": 39,
          "answered": 40,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.975
        },
        "F07": {
          "n": 76,
          "correct": 50,
          "answered": 76,
          "failed": 0,
          "wrong_valid": 26,
          "accuracy": 0.6578947368421053
        },
        "F08": {
          "n": 67,
          "correct": 65,
          "answered": 67,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9701492537313433
        },
        "F09": {
          "n": 71,
          "correct": 42,
          "answered": 71,
          "failed": 0,
          "wrong_valid": 29,
          "accuracy": 0.5915492957746479
        },
        "F10": {
          "n": 74,
          "correct": 53,
          "answered": 74,
          "failed": 0,
          "wrong_valid": 21,
          "accuracy": 0.7162162162162162
        },
        "F11": {
          "n": 41,
          "correct": 35,
          "answered": 41,
          "failed": 0,
          "wrong_valid": 6,
          "accuracy": 0.8536585365853658
        },
        "F12": {
          "n": 52,
          "correct": 29,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 23,
          "accuracy": 0.5576923076923077
        },
        "F13": {
          "n": 48,
          "correct": 18,
          "answered": 48,
          "failed": 0,
          "wrong_valid": 30,
          "accuracy": 0.375
        },
        "F14": {
          "n": 42,
          "correct": 40,
          "answered": 42,
          "failed": 0,
          "wrong_valid": 2,
          "accuracy": 0.9523809523809523
        },
        "F15": {
          "n": 49,
          "correct": 40,
          "answered": 49,
          "failed": 0,
          "wrong_valid": 9,
          "accuracy": 0.8163265306122449
        },
        "F16": {
          "n": 50,
          "correct": 39,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 11,
          "accuracy": 0.78
        },
        "F17": {
          "n": 50,
          "correct": 46,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.92
        },
        "F18": {
          "n": 50,
          "correct": 46,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.92
        },
        "F19": {
          "n": 58,
          "correct": 54,
          "answered": 58,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.9310344827586207
        },
        "F20": {
          "n": 43,
          "correct": 39,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.9069767441860465
        },
        "F21": {
          "n": 43,
          "correct": 42,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9767441860465116
        },
        "F22": {
          "n": 51,
          "correct": 48,
          "answered": 51,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.9411764705882353
        },
        "F23": {
          "n": 52,
          "correct": 52,
          "answered": 52,
          "failed": 0,
          "wrong_valid": 0,
          "accuracy": 1.0
        },
        "F24": {
          "n": 43,
          "correct": 42,
          "answered": 43,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.9767441860465116
        },
        "F25": {
          "n": 50,
          "correct": 46,
          "answered": 50,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.92
        },
        "F26": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.625
        },
        "F27": {
          "n": 8,
          "correct": 4,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 4,
          "accuracy": 0.5
        },
        "F28": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.625
        },
        "F29": {
          "n": 8,
          "correct": 5,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 3,
          "accuracy": 0.625
        },
        "F30": {
          "n": 8,
          "correct": 3,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 5,
          "accuracy": 0.375
        },
        "F31": {
          "n": 8,
          "correct": 7,
          "answered": 8,
          "failed": 0,
          "wrong_valid": 1,
          "accuracy": 0.875
        }
      },
      "dates_toronto": {
        "2026-10-21": 1342
      },
      "returned_identities": {
        "nace-ai/drex-max-20261016": 1342
      },
      "providers": {
        "DeepInfra": 1342
      },
      "route": "OpenRouter \u2192 DeepInfra \u2192 nace-ai/drex-max",
      "output_token_values": {
        "169": 177,
        "170": 263,
        "171": 212,
        "160": 34,
        "164": 44,
        "173": 32,
        "162": 68,
        "168": 94,
        "159": 11,
        "163": 70,
        "165": 50,
        "167": 49,
        "172": 117,
        "157": 2,
        "161": 65,
        "166": 45,
        "158": 8,
        "156": 1
      },
      "input_tokens": 473717,
      "macro_family_accuracy": 0.8109694050743982,
      "new_domains": {
        "n": 48,
        "correct": 29,
        "answered": 48,
        "failed": 0,
        "wrong_valid": 19,
        "accuracy": 0.6041666666666666
      },
      "release_exclusion_diagnostic": {
        "n": 1305,
        "correct": 1112,
        "answered": 1305,
        "failed": 0,
        "wrong_valid": 193,
        "accuracy": 0.8521072796934865
      },
      "original_1136": {
        "n": 1136,
        "correct": 1004,
        "answered": 1136,
        "failed": 0,
        "wrong_valid": 132,
        "accuracy": 0.8838028169014085
      },
      "added_206": {
        "n": 206,
        "correct": 123,
        "answered": 206,
        "failed": 0,
        "wrong_valid": 83,
        "accuracy": 0.5970873786407767
      },
      "compatibility": {
        "status": "ok",
        "reported_cost_usd": 7.2e-06,
        "accounted_cost_usd": 7.2e-06,
        "cost_source": "api_reported"
      }
    }
  },
  "uniform_guess_baseline": 0.2,
  "limits": [
    "One consolidated development overview, not a held-out scored release;37 author-development cases retain permanent release exclusions.",
    "Questions include dependent variants, correlated model routes, and unbalanced category counts. No independent-trial confidence claims.",
    "Six domains have8 questions each; their apparent perfect scores are not reliability guarantees.",
    "Timing pools retain original test dates, providers and request loads; this was not a synchronized rerun.",
    "Costs retain captured API charges/tariffs; unknown costs are lower bounds, not zero.",
    "First-attempt provider failures are unsuccessful delivered decisions, not wrong reasoning answers.",
    "Ordinary LLMs without complete1342 coverage are references only, never ranked against the full-bank cohort.",
    "No new model calls, unchanged question reruns or model removals. This is a public developmental overview, not a held-out release."
  ],
  "latency_definition": "Median and linearly interpolated p95 from all1342 raw first-attempt durations; includes failures, excludes retry durations and wait/queue times.",
  "reference_model_ids": [
    "reference_sol",
    "reference_sonnet",
    "reference_qwen"
  ],
  "tested_llm_reference_count": 3,
  "all_tested_primary_cases": 38918,
  "decision_model_ids": [
    "mammoth1",
    "drex_max",
    "respan02",
    "pplx_decider12",
    "nimble_v4_max",
    "d3_turbo",
    "liquid_ultra",
    "amos_large",
    "kettei_fat",
    "jev114",
    "jev113",
    "mercury_decide",
    "elephant1",
    "liquid_d1",
    "clef",
    "pplx_flash12",
    "microsoft_decision",
    "drex20",
    "clef_flash",
    "clef_omni",
    "drex15",
    "kev4b",
    "luna_decisions",
    "tev1_4b_native",
    "classify1",
    "solar_flash"
  ],
  "model_kinds": {
    "respan02": "Decision model",
    "pplx_decider12": "Decision model",
    "nimble_v4_max": "Decision model",
    "jev114": "Decision model",
    "liquid_ultra": "Decision model",
    "mercury_decide": "Decision model",
    "jev113": "Decision model",
    "luna_decisions": "Decision model",
    "microsoft_decision": "Decision model",
    "liquid_d1": "Decision model",
    "pplx_flash12": "Decision model",
    "clef": "Decision model",
    "clef_flash": "Decision model",
    "clef_omni": "Decision model",
    "solar_flash": "Decision model",
    "drex20": "Decision model",
    "drex15": "Decision model",
    "classify1": "Decision model",
    "kev4b": "Decision model",
    "tev1_4b_native": "Decision model",
    "reference_sol": "LLM reference",
    "reference_sonnet": "LLM reference",
    "reference_qwen": "LLM reference",
    "d3_turbo": "Decision model",
    "amos_large": "Decision model",
    "kettei_fat": "Decision model",
    "mammoth1": "Decision model",
    "elephant1": "Decision model",
    "drex_max": "Decision model"
  },
  "source_native_statistics_sha256": "e1348fb78c3b5bdc88874ba4af23681f37aaa972414d8910b7ce401c3a730950",
  "reference_evidence_bindings": {
    "reference_sol": {
      "source_summary_sha256": "fb440bc91730ab5e0c6974d283cf5f73602105f9eb0017a0ffb771a49f637e92",
      "completion_sha256": "a4906472c00c336c8b0ef312f215abc0ee6610295d3cd36fcea04298eb5db821",
      "private_source_scoring_bindings": [
        "33a04e1b7ac8b3a3020423a37781e1ca5a3939081c6d350fd6a532a00bad77c2",
        "3b41037fba1cb02f42d0044a0dd758f1cc588de86fe0d2a5f90b142a41f353bb",
        "471b808d20d9be2608ef60fddbf8526bf9015af3d6a4d976b7a2b20843ad46e1",
        "4ca81b991c4002e70aead0d56b9f53c21f1e70d9b1fef1a4a1f2e32f32d5b56c",
        "4cd7c58fe4be67dadb3644fc54d46d8e4a40aaa8ed73c2005b6dbe52a4341a36",
        "6cb31d4192e256c5b6fa56d480025634bfbdca9ce8b2b68558ed44fe6bfa6c69",
        "8376ddce67cd9bb5f62d685d0309b4de5706f091084fbe72aed7dc91d1bf4dec",
        "aac4b2c2ece0f6cf37b81794031d93a8c3f53d032da1eb127d14f62be34781a6",
        "b5dba10a8c9fbcbd0fc79f62e11a9a08594fdc187cf3ead7b5bb872a43bf1b5f",
        "bb7ff1f81ac1b35bb93c25a5ac7dce48a0d86ff48cda711304b9932864c1bc3a",
        "c99db093ae3517dcacc03319f00a461acbfd19e0eb22cb0c5a5dd636f1ee9271",
        "ca5aa924ee10efe60bca09e02bb7fbb68740d12b243ca7bd619ceb5fc952c7bb",
        "dbac830fe3cad5f469f950fe2c3b1c2e575cb6d00c2bdaec4b82c46f41b0b8ab",
        "f6f685ea96ebd626804931278e03256bd502f0dc811a8694d9417a4ad5b64c01",
        "fbe6f2b49ad7c99416fb45dc05b8b9db37a3850017d7bfef81644d09afe9bcd4"
      ],
      "operational_evidence": {}
    },
    "reference_sonnet": {
      "source_summary_sha256": "a35287115c5f86a381b8ab420407f52051c2cba6689717406b033e5093bc7f0c",
      "completion_sha256": "96a498a27d8cb92845a5e867ce89c303e2501081307b7003e7ef65ce088244f2",
      "private_source_scoring_bindings": [
        "33a04e1b7ac8b3a3020423a37781e1ca5a3939081c6d350fd6a532a00bad77c2",
        "3b41037fba1cb02f42d0044a0dd758f1cc588de86fe0d2a5f90b142a41f353bb",
        "471b808d20d9be2608ef60fddbf8526bf9015af3d6a4d976b7a2b20843ad46e1",
        "4ca81b991c4002e70aead0d56b9f53c21f1e70d9b1fef1a4a1f2e32f32d5b56c",
        "4cd7c58fe4be67dadb3644fc54d46d8e4a40aaa8ed73c2005b6dbe52a4341a36",
        "6cb31d4192e256c5b6fa56d480025634bfbdca9ce8b2b68558ed44fe6bfa6c69",
        "8376ddce67cd9bb5f62d685d0309b4de5706f091084fbe72aed7dc91d1bf4dec",
        "aac4b2c2ece0f6cf37b81794031d93a8c3f53d032da1eb127d14f62be34781a6",
        "b5dba10a8c9fbcbd0fc79f62e11a9a08594fdc187cf3ead7b5bb872a43bf1b5f",
        "bb7ff1f81ac1b35bb93c25a5ac7dce48a0d86ff48cda711304b9932864c1bc3a",
        "c99db093ae3517dcacc03319f00a461acbfd19e0eb22cb0c5a5dd636f1ee9271",
        "ca5aa924ee10efe60bca09e02bb7fbb68740d12b243ca7bd619ceb5fc952c7bb",
        "dbac830fe3cad5f469f950fe2c3b1c2e575cb6d00c2bdaec4b82c46f41b0b8ab",
        "f6f685ea96ebd626804931278e03256bd502f0dc811a8694d9417a4ad5b64c01",
        "fbe6f2b49ad7c99416fb45dc05b8b9db37a3850017d7bfef81644d09afe9bcd4"
      ],
      "operational_evidence": {}
    },
    "reference_qwen": {
      "source_summary_sha256": "ce52e97aaec9dff8137852ce917e065cde038f5c370622589b5f0c235d638331",
      "completion_sha256": "bc5bda846e49c4545ce4e3d00f4b19c6f7a4315f3f46299a5b95435b3019ac38",
      "private_source_scoring_bindings": [
        "33a04e1b7ac8b3a3020423a37781e1ca5a3939081c6d350fd6a532a00bad77c2",
        "3b41037fba1cb02f42d0044a0dd758f1cc588de86fe0d2a5f90b142a41f353bb",
        "471b808d20d9be2608ef60fddbf8526bf9015af3d6a4d976b7a2b20843ad46e1",
        "4ca81b991c4002e70aead0d56b9f53c21f1e70d9b1fef1a4a1f2e32f32d5b56c",
        "4cd7c58fe4be67dadb3644fc54d46d8e4a40aaa8ed73c2005b6dbe52a4341a36",
        "6cb31d4192e256c5b6fa56d480025634bfbdca9ce8b2b68558ed44fe6bfa6c69",
        "8376ddce67cd9bb5f62d685d0309b4de5706f091084fbe72aed7dc91d1bf4dec",
        "aac4b2c2ece0f6cf37b81794031d93a8c3f53d032da1eb127d14f62be34781a6",
        "b5dba10a8c9fbcbd0fc79f62e11a9a08594fdc187cf3ead7b5bb872a43bf1b5f",
        "bb7ff1f81ac1b35bb93c25a5ac7dce48a0d86ff48cda711304b9932864c1bc3a",
        "c99db093ae3517dcacc03319f00a461acbfd19e0eb22cb0c5a5dd636f1ee9271",
        "ca5aa924ee10efe60bca09e02bb7fbb68740d12b243ca7bd619ceb5fc952c7bb",
        "dbac830fe3cad5f469f950fe2c3b1c2e575cb6d00c2bdaec4b82c46f41b0b8ab",
        "f6f685ea96ebd626804931278e03256bd502f0dc811a8694d9417a4ad5b64c01",
        "fbe6f2b49ad7c99416fb45dc05b8b9db37a3850017d7bfef81644d09afe9bcd4"
      ],
      "operational_evidence": {
        "operator_events.jsonl": "ea476ad58192f6a79368dfd4ea53adb0d48cec347379b70db4e39f45dd365abc",
        "provider_cooldown.json": "4a659427b0e9833596ddc39b9a18b7b82c109dd63d0d9ba11c93ee44056423b0",
        "provider_cooldown_extension.json": "333b79894b3662389f76873467cd1c3ed32ceca5bf6b5bc1ab3fc4142b419045",
        "pacing_receipt.json": "12111cf8279413f890c138902870abeed5f969c3989bf35200a4191a03a416e4",
        "pacing_waits.jsonl": "d6abe3197024998697a681a14cd2133ccf1a5cc37886adeec5072d97048d12c3"
      }
    }
  },
  "question_bank_sha256": "2db8cf8353f12b609d4df5330d94f53390c9c2919677dc793df4bb2d3cff7076",
  "decision_model_count": 26,
  "added_model_ids": [
    "mammoth1",
    "elephant1",
    "drex_max"
  ],
  "updated_date_toronto": "2026-10-21",
  "prior_statistics_sha256": "c31683c5e211e301a6389f770b2441e12b66e2f80f9c3a124fdbfc166165a4b0",
  "direct_evidence_bindings": {
    "d3_turbo": {
      "manifest.json": "e2dddd70e2ff6e887751bdc05f50cf01d72068bb9278e77ae923736fdf5163fe",
      "software.json": "a6a99bb579834587f2dcb5a34452b2ab4632ba4f8fe4ce2bfc0062c18ca27efe",
      "model_metadata.json": "a32ae0e379f4925c9bf07894b2853ac789ff92f5dc274250ba732c88bad0f7c5",
      "probe_dispatch.json": "2b4f8c34e467b55807817eeb2c160fdfcdc4dba08b54e9cf95bc06e208c6413b",
      "compatibility_probe.json": "80eaf0b091526becdfb21ef312f14709231387c37d4343004d685cba59e38e4d",
      "dispatches.jsonl": "3a23e59f60d2fa643f02c014e56080a452529fcdbcf8f4c91d6429a0564b0a94",
      "attempts.jsonl": "aabe666145d6a24bbd504c2cf0f2a181d585ff2f8ef8353d2ddfa5e41bc03021",
      "results.jsonl": "e3ef638cfb6b094fe624a86f3e378d0e5c93fdc9f360744ed7a66052f4b562c6",
      "completion.json": "26c9687c4031db7d957937cebd5bf5391f2955b4b3574600f324fb86e9c8fc2e"
    },
    "amos_large": {
      "manifest.json": "e0647fdf0743969bf08e668bbdf2896630e51bfe910ae40cc7409350807c2fae",
      "software.json": "a6a99bb579834587f2dcb5a34452b2ab4632ba4f8fe4ce2bfc0062c18ca27efe",
      "model_metadata.json": "e2a4e3a59cf87dc708ab25103db2d82bc46bceeeed201f9cac8e409849a88503",
      "probe_dispatch.json": "ae5045ac0325920cc46d9ccd9d6b91b9e321c8e7846434fd99dc45155bd15d7c",
      "compatibility_probe.json": "923ec73d8ad96a8367088603ef6d67e7e1e400c468c25dd67ab751c73dc19bcb",
      "dispatches.jsonl": "a09a139f6f685c488c8fbd6d4eb56700fde8635ec9827360888e5ee50437e29e",
      "attempts.jsonl": "2ab2ffbb01ec7ab609839b5b3cdcd7d92496a771d76009ae8d9df438bf6fbe37",
      "results.jsonl": "0189941dd1502ad63ecf55e44879fb63f768c67e1d1204f213d006cc2ece7e68",
      "completion.json": "8789c3d8969e4e2c111800e16edd5dc74bdf9fda8e81c063c2e9fcec90d6c831"
    },
    "kettei_fat": {
      "manifest.json": "c0fb09c04bba4eb6fcaeaceb643b729f85552291b3805dac7e754ed286d55943",
      "software.json": "a6a99bb579834587f2dcb5a34452b2ab4632ba4f8fe4ce2bfc0062c18ca27efe",
      "model_metadata.json": "3842b8979235fea42e52fd867414ec12d89181a777ac7f00646af4cff0f65980",
      "probe_dispatch.json": "8f632423adcee7d2b1b6022b4caa82c03f9259eac6c82af392e7c1284889f8f4",
      "compatibility_probe.json": "f115a687b4ef4850105e4eb0beebf419da424e5493cd7c6d40cdf8c4f735190b",
      "dispatches.jsonl": "32f2d6f80726a98096a5b38832a187c6f1cb9cc6aeae60035e86c6e5d67c47ef",
      "attempts.jsonl": "7c20266cdad35eeefd2eeeff19e3309f0b328fb4b3980eb7d00091201f946c38",
      "results.jsonl": "eb4d4e73cabf177a82031d33fe77ce22a6f51748430920d1164a6f4e3ef5b849",
      "completion.json": "dd1a5b0444b9a841bb142857c5444f0f41c94ec4d4b04aec4d7bce5227cb24f7",
      "account_rate_amendment.json": "87c84f03393d1072ea99784d59280fdd139e865a897038a658207515375e68ac"
    }
  },
  "direct_source_summary_sha256": "6bd97c172fb1ba44ed8c9ee731aeaab6b6fd876184f3c45c066468c452f7b573",
  "direct_scoring_authority_sha256": [
    "33a04e1b7ac8b3a3020423a37781e1ca5a3939081c6d350fd6a532a00bad77c2",
    "3b41037fba1cb02f42d0044a0dd758f1cc588de86fe0d2a5f90b142a41f353bb",
    "471b808d20d9be2608ef60fddbf8526bf9015af3d6a4d976b7a2b20843ad46e1",
    "4ca81b991c4002e70aead0d56b9f53c21f1e70d9b1fef1a4a1f2e32f32d5b56c",
    "4cd7c58fe4be67dadb3644fc54d46d8e4a40aaa8ed73c2005b6dbe52a4341a36",
    "8376ddce67cd9bb5f62d685d0309b4de5706f091084fbe72aed7dc91d1bf4dec",
    "aac4b2c2ece0f6cf37b81794031d93a8c3f53d032da1eb127d14f62be34781a6",
    "b5dba10a8c9fbcbd0fc79f62e11a9a08594fdc187cf3ead7b5bb872a43bf1b5f",
    "bb7ff1f81ac1b35bb93c25a5ac7dce48a0d86ff48cda711304b9932864c1bc3a",
    "c99db093ae3517dcacc03319f00a461acbfd19e0eb22cb0c5a5dd636f1ee9271",
    "ca5aa924ee10efe60bca09e02bb7fbb68740d12b243ca7bd619ceb5fc952c7bb",
    "dbac830fe3cad5f469f950fe2c3b1c2e575cb6d00c2bdaec4b82c46f41b0b8ab",
    "f6f685ea96ebd626804931278e03256bd502f0dc811a8694d9417a4ad5b64c01",
    "fbe6f2b49ad7c99416fb45dc05b8b9db37a3850017d7bfef81644d09afe9bcd4"
  ],
  "direct_analysis_source_sha256": {
    "analyze_direct_decisions_2026_10_20.py": "2517c3e6f8d32d2a9e0d403d8fc7a02f883883c42a3e008f7453addd43384916",
    "test_analyze_direct_decisions_2026_10_20.py": "526ad74fedc0f49e184aa62a246309667ef908bd7d002d7af72788ab792f0497",
    "llm_references_2026-10-19/statistics.json": "cff708651203a54f3ddb7e17782f8c2abdbc8900a92f81d7492afa6e8a90b435",
    "llm_references_2026-10-19/category_guide.json": "183f7fa8ace26704616423f307e0d8f0acb923a6b29c78e837ebf1ddaa7be823"
  },
  "total_http_attempts": 39084,
  "total_recoveries": 166
}
