{
 "schema_version": "1.3",
 "snapshot_date": "2026-09-13",
 "published_at": "2026-09-13T15:39:32Z",
 "dispositions": {
  "DENY": "Measured finding. Confidently wrong more often than right beyond measurement noise, or scoring zero on an in-scope evaluation while still billing.",
  "REVIEW": "Not a measured integrity failure. Either under our stated efficacy bar, which is a parameter you may set differently, or inside the honesty noise band, which is absence of evidence rather than evidence of failure. Approved rows are not here; their honesty GRADE (A, B, C) is in the snapshot and says where each may run."
 },
 "counts": {
  "DENY": 24,
  "REVIEW": 26
 },
 "by_reason": {
  "BELOW_EFFICACY": 20,
  "COST_UNDEFINED": 4,
  "FAILS_HONESTY": 20,
  "HONESTY_INCONCLUSIVE": 6
 },
 "match_coverage": {
  "confirmed": 18,
  "unmapped": 32,
  "note": "An unmapped row is still a policy statement. API identifiers are never guessed."
 },
 "configurations": [
  {
   "id": "openai/gpt-5.6-luna@low",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "OpenAI",
   "model": "GPT-5.6 Luna",
   "effort": "low",
   "honesty_net_per_100": -14.65,
   "honesty_answers_when_unsure_pct": 89.8703,
   "honesty_confident_errors_per_100": 54.2667,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.5461,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {
     "openai": [
      "gpt-5.6-luna"
     ],
     "zaun_gateway": [
      "openai.gpt-5.6-luna"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=openai/gpt-5.6-luna@low"
  },
  {
   "id": "openai/gpt-5.6-luna@medium",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "OpenAI",
   "model": "GPT-5.6 Luna",
   "effort": "medium",
   "honesty_net_per_100": -13.18,
   "honesty_answers_when_unsure_pct": 90.8657,
   "honesty_confident_errors_per_100": 53.8833,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.6109,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {
     "openai": [
      "gpt-5.6-luna"
     ],
     "zaun_gateway": [
      "openai.gpt-5.6-luna"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=openai/gpt-5.6-luna@medium"
  },
  {
   "id": "openai/gpt-5.6-luna@non-reasoning",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "OpenAI",
   "model": "GPT-5.6 Luna",
   "effort": "non-reasoning",
   "honesty_net_per_100": -24.95,
   "honesty_answers_when_unsure_pct": 75.0,
   "honesty_confident_errors_per_100": 53.55,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.3893,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {
     "openai": [
      "gpt-5.6-luna"
     ],
     "zaun_gateway": [
      "openai.gpt-5.6-luna"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=openai/gpt-5.6-luna@non-reasoning"
  },
  {
   "id": "openai/gpt-5.6-luna@high",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "OpenAI",
   "model": "GPT-5.6 Luna",
   "effort": "high",
   "honesty_net_per_100": -12.0,
   "honesty_answers_when_unsure_pct": 92.3848,
   "honesty_confident_errors_per_100": 53.7833,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.7457,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {
     "openai": [
      "gpt-5.6-luna"
     ],
     "zaun_gateway": [
      "openai.gpt-5.6-luna"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=openai/gpt-5.6-luna@high"
  },
  {
   "id": "openai/gpt-5.6-luna@xhigh",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "OpenAI",
   "model": "GPT-5.6 Luna",
   "effort": "xhigh",
   "honesty_net_per_100": -10.77,
   "honesty_answers_when_unsure_pct": 92.4703,
   "honesty_confident_errors_per_100": 53.2167,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.7887,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {
     "openai": [
      "gpt-5.6-luna"
     ],
     "zaun_gateway": [
      "openai.gpt-5.6-luna"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=openai/gpt-5.6-luna@xhigh"
  },
  {
   "id": "zai/glm-5.3-flash@default",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "Z.ai",
   "model": "GLM-5.3-Flash",
   "effort": "default",
   "honesty_net_per_100": 7.4667,
   "honesty_answers_when_unsure_pct": 27.6322,
   "honesty_confident_errors_per_100": 20.0333,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.7834,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=zai/glm-5.3-flash@default"
  },
  {
   "id": "openai/gpt-5.6-luna@max",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "OpenAI",
   "model": "GPT-5.6 Luna",
   "effort": "max",
   "honesty_net_per_100": -10.28,
   "honesty_answers_when_unsure_pct": 92.5786,
   "honesty_confident_errors_per_100": 53.0167,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.8207,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {
     "openai": [
      "gpt-5.6-luna"
     ],
     "zaun_gateway": [
      "openai.gpt-5.6-luna"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=openai/gpt-5.6-luna@max"
  },
  {
   "id": "google/gemini-3.7-flash@low",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "Google",
   "model": "Gemini 3.7 Flash",
   "effort": "low",
   "honesty_net_per_100": 22.13,
   "honesty_answers_when_unsure_pct": 67.6956,
   "honesty_confident_errors_per_100": 31.4333,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.7306,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=google/gemini-3.7-flash@low"
  },
  {
   "id": "alibaba/qwen3.8-flash-next@default",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "Alibaba",
   "model": "Qwen3.8-Flash-Next",
   "effort": "default",
   "honesty_net_per_100": -9.7167,
   "honesty_answers_when_unsure_pct": 45.3201,
   "honesty_confident_errors_per_100": 34.2167,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.7617,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=alibaba/qwen3.8-flash-next@default"
  },
  {
   "id": "google/gemini-3.8-flash@low",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "Google",
   "model": "Gemini 3.8 Flash",
   "effort": "low",
   "honesty_net_per_100": 21.35,
   "honesty_answers_when_unsure_pct": 64.5971,
   "honesty_confident_errors_per_100": 30.8667,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.7394,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=google/gemini-3.8-flash@low"
  },
  {
   "id": "google/gemini-3.7-flash@medium",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "Google",
   "model": "Gemini 3.7 Flash",
   "effort": "medium",
   "honesty_net_per_100": 23.7,
   "honesty_answers_when_unsure_pct": 65.8696,
   "honesty_confident_errors_per_100": 30.3,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.7784,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=google/gemini-3.7-flash@medium"
  },
  {
   "id": "deepseek/deepseek-v4-pro@high",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "DeepSeek",
   "model": "DeepSeek V4 Pro",
   "effort": "high",
   "honesty_net_per_100": -10.5667,
   "honesty_answers_when_unsure_pct": 88.6803,
   "honesty_confident_errors_per_100": 51.9667,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.6845,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=deepseek/deepseek-v4-pro@high"
  },
  {
   "id": "openai/gpt-5.6-terra@non-reasoning",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "OpenAI",
   "model": "GPT-5.6 Terra",
   "effort": "non-reasoning",
   "honesty_net_per_100": -23.22,
   "honesty_answers_when_unsure_pct": 95.0145,
   "honesty_confident_errors_per_100": 60.0333,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.504,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {
     "openai": [
      "gpt-5.6-terra"
     ],
     "zaun_gateway": [
      "openai.gpt-5.6-terra"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=openai/gpt-5.6-terra@non-reasoning"
  },
  {
   "id": "openai/gpt-5.6-terra@low",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "OpenAI",
   "model": "GPT-5.6 Terra",
   "effort": "low",
   "honesty_net_per_100": -6.83,
   "honesty_answers_when_unsure_pct": 89.8697,
   "honesty_confident_errors_per_100": 50.5667,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.6604,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {
     "openai": [
      "gpt-5.6-terra"
     ],
     "zaun_gateway": [
      "openai.gpt-5.6-terra"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=openai/gpt-5.6-terra@low"
  },
  {
   "id": "xai/grok-4.6@low",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "xAI",
   "model": "Grok 4.6",
   "effort": "low",
   "honesty_net_per_100": 25.9,
   "honesty_answers_when_unsure_pct": 30.6494,
   "honesty_confident_errors_per_100": 17.3833,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.6842,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=xai/grok-4.6@low"
  },
  {
   "id": "deepseek/deepseek-v4-pro@max",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "DeepSeek",
   "model": "DeepSeek V4 Pro",
   "effort": "max",
   "honesty_net_per_100": -10.7333,
   "honesty_answers_when_unsure_pct": 94.0987,
   "honesty_confident_errors_per_100": 53.6833,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.7171,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=deepseek/deepseek-v4-pro@max"
  },
  {
   "id": "openai/gpt-5.6-terra@medium",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "OpenAI",
   "model": "GPT-5.6 Terra",
   "effort": "medium",
   "honesty_net_per_100": -5.13,
   "honesty_answers_when_unsure_pct": 89.7714,
   "honesty_confident_errors_per_100": 49.7333,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.7407,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {
     "openai": [
      "gpt-5.6-terra"
     ],
     "zaun_gateway": [
      "openai.gpt-5.6-terra"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=openai/gpt-5.6-terra@medium"
  },
  {
   "id": "deepseek/deepseek-v4-flash-0731@max",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "DeepSeek",
   "model": "DeepSeek V4 Flash 0731",
   "effort": "max",
   "honesty_net_per_100": -14.2833,
   "honesty_answers_when_unsure_pct": 91.697,
   "honesty_confident_errors_per_100": 54.6667,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.7776,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=deepseek/deepseek-v4-flash-0731@max"
  },
  {
   "id": "deepseek/deepseek-v4-flash-vision@max",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "DeepSeek",
   "model": "DeepSeek V4 Flash Vision",
   "effort": "max",
   "honesty_net_per_100": -17.6333,
   "honesty_answers_when_unsure_pct": 91.4813,
   "honesty_confident_errors_per_100": 56.2,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.728,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=deepseek/deepseek-v4-flash-vision@max"
  },
  {
   "id": "google/gemini-3.8-flash@medium",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "Google",
   "model": "Gemini 3.8 Flash",
   "effort": "medium",
   "honesty_net_per_100": 28.58,
   "honesty_answers_when_unsure_pct": 51.8965,
   "honesty_confident_errors_per_100": 24.4,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.8074,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=google/gemini-3.8-flash@medium"
  },
  {
   "id": "openai/gpt-5.6-sol@non-reasoning",
   "disposition": "REVIEW",
   "reason_code": "HONESTY_INCONCLUSIVE",
   "vendor": "OpenAI",
   "model": "GPT-5.6 Sol",
   "effort": "non-reasoning",
   "honesty_net_per_100": 1.1,
   "honesty_answers_when_unsure_pct": 92.7875,
   "honesty_confident_errors_per_100": 47.6,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.5861,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {
     "openai": [
      "gpt-5.6-sol"
     ],
     "zaun_gateway": [
      "openai.gpt-5.6-sol"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=openai/gpt-5.6-sol@non-reasoning"
  },
  {
   "id": "openai/gpt-5.6-sol@low",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "OpenAI",
   "model": "GPT-5.6 Sol",
   "effort": "low",
   "honesty_net_per_100": 18.87,
   "honesty_answers_when_unsure_pct": 89.4163,
   "honesty_confident_errors_per_100": 38.3,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.7784,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {
     "openai": [
      "gpt-5.6-sol"
     ],
     "zaun_gateway": [
      "openai.gpt-5.6-sol"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=openai/gpt-5.6-sol@low"
  },
  {
   "id": "minimax/minimax-m3@default",
   "disposition": "REVIEW",
   "reason_code": "HONESTY_INCONCLUSIVE",
   "vendor": "MiniMax",
   "model": "MiniMax-M3",
   "effort": "default",
   "honesty_net_per_100": 1.35,
   "honesty_answers_when_unsure_pct": 18.4274,
   "honesty_confident_errors_per_100": 15.35,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.6914,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=minimax/minimax-m3@default"
  },
  {
   "id": "google/gemini-3.7-flash@high",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "Google",
   "model": "Gemini 3.7 Flash",
   "effort": "high",
   "honesty_net_per_100": 26.48,
   "honesty_answers_when_unsure_pct": 64.5282,
   "honesty_confident_errors_per_100": 28.8333,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.8416,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=google/gemini-3.7-flash@high"
  },
  {
   "id": "nvidia/nemotron-3-super-120b-a12b@reasoning",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "NVIDIA",
   "model": "Nemotron 3 Super 120B A12B",
   "effort": "reasoning",
   "honesty_net_per_100": -41.5,
   "honesty_answers_when_unsure_pct": 86.9632,
   "honesty_confident_errors_per_100": 65.8167,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.501,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=nvidia/nemotron-3-super-120b-a12b@reasoning"
  },
  {
   "id": "openai/gpt-5.6-terra@high",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "OpenAI",
   "model": "GPT-5.6 Terra",
   "effort": "high",
   "honesty_net_per_100": -3.47,
   "honesty_answers_when_unsure_pct": 89.7891,
   "honesty_confident_errors_per_100": 48.95,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.8012,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {
     "openai": [
      "gpt-5.6-terra"
     ],
     "zaun_gateway": [
      "openai.gpt-5.6-terra"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=openai/gpt-5.6-terra@high"
  },
  {
   "id": "moonshot/kimi-k3@low",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "Moonshot",
   "model": "Kimi K3",
   "effort": "low",
   "honesty_net_per_100": 3.9167,
   "honesty_answers_when_unsure_pct": 77.1121,
   "honesty_confident_errors_per_100": 41.8333,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.6743,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=moonshot/kimi-k3@low"
  },
  {
   "id": "openai/gpt-6-astra@non-reasoning",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "OpenAI",
   "model": "GPT-6 Astra",
   "effort": "non-reasoning",
   "honesty_net_per_100": 26.55,
   "honesty_answers_when_unsure_pct": 65.4279,
   "honesty_confident_errors_per_100": 29.05,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.7955,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=openai/gpt-6-astra@non-reasoning"
  },
  {
   "id": "alibaba/qwen3.8-27b@non-reasoning",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "Alibaba",
   "model": "Qwen3.8 27B",
   "effort": "non-reasoning",
   "honesty_net_per_100": -7.95,
   "honesty_answers_when_unsure_pct": 18.0857,
   "honesty_confident_errors_per_100": 16.5333,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.4887,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=alibaba/qwen3.8-27b@non-reasoning"
  },
  {
   "id": "openai/gpt-5.6-terra@xhigh",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "OpenAI",
   "model": "GPT-5.6 Terra",
   "effort": "xhigh",
   "honesty_net_per_100": -2.98,
   "honesty_answers_when_unsure_pct": 89.018,
   "honesty_confident_errors_per_100": 48.5,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.85,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {
     "openai": [
      "gpt-5.6-terra"
     ],
     "zaun_gateway": [
      "openai.gpt-5.6-terra"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=openai/gpt-5.6-terra@xhigh"
  },
  {
   "id": "anthropic/claude-sonnet-5@non-reasoning",
   "disposition": "REVIEW",
   "reason_code": "HONESTY_INCONCLUSIVE",
   "vendor": "Anthropic",
   "model": "Claude Sonnet 5",
   "effort": "non-reasoning",
   "honesty_net_per_100": -0.65,
   "honesty_answers_when_unsure_pct": 52.0393,
   "honesty_confident_errors_per_100": 34.45,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.5977,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {
     "anthropic": [
      "claude-sonnet-5"
     ],
     "bedrock": [
      "us.anthropic.claude-sonnet-5"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=anthropic/claude-sonnet-5@non-reasoning"
  },
  {
   "id": "xai/grok-4.6@medium",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "xAI",
   "model": "Grok 4.6",
   "effort": "medium",
   "honesty_net_per_100": 28.0,
   "honesty_answers_when_unsure_pct": 23.9954,
   "honesty_confident_errors_per_100": 13.9333,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.8178,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=xai/grok-4.6@medium"
  },
  {
   "id": "moonshot/kimi-k2.7-code@default",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "Moonshot",
   "model": "Kimi K2.7 Code",
   "effort": "default",
   "honesty_net_per_100": -10.2167,
   "honesty_answers_when_unsure_pct": 82.3773,
   "honesty_confident_errors_per_100": 49.7833,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.706,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=moonshot/kimi-k2.7-code@default"
  },
  {
   "id": "anthropic/claude-opus-5@low",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "Anthropic",
   "model": "Claude Opus 5",
   "effort": "low",
   "honesty_net_per_100": 28.55,
   "honesty_answers_when_unsure_pct": 62.202,
   "honesty_confident_errors_per_100": 27.4,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.8179,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {
     "anthropic": [
      "claude-opus-5"
     ],
     "bedrock": [
      "us.anthropic.claude-opus-5"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=anthropic/claude-opus-5@low"
  },
  {
   "id": "xai/grok-4.6@high",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "xAI",
   "model": "Grok 4.6",
   "effort": "high",
   "honesty_net_per_100": 30.48,
   "honesty_answers_when_unsure_pct": 34.2885,
   "honesty_confident_errors_per_100": 17.75,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.8288,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=xai/grok-4.6@high"
  },
  {
   "id": "meta/muse-spark-1.2@xhigh",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "Meta",
   "model": "Muse Spark 1.2",
   "effort": "xhigh",
   "honesty_net_per_100": 27.2,
   "honesty_answers_when_unsure_pct": 33.2926,
   "honesty_confident_errors_per_100": 18.1833,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.8405,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=meta/muse-spark-1.2@xhigh"
  },
  {
   "id": "xai/grok-4.6@xhigh",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "xAI",
   "model": "Grok 4.6",
   "effort": "xhigh",
   "honesty_net_per_100": 29.32,
   "honesty_answers_when_unsure_pct": 24.0058,
   "honesty_confident_errors_per_100": 13.6833,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.8385,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=xai/grok-4.6@xhigh"
  },
  {
   "id": "deepseek/deepseek-v4-pro-0813@max",
   "disposition": "REVIEW",
   "reason_code": "HONESTY_INCONCLUSIVE",
   "vendor": "DeepSeek",
   "model": "DeepSeek V4 Pro 0813",
   "effort": "max",
   "honesty_net_per_100": 0.83,
   "honesty_answers_when_unsure_pct": 94.8265,
   "honesty_confident_errors_per_100": 48.2667,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.7955,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=deepseek/deepseek-v4-pro-0813@max"
  },
  {
   "id": "nvidia/nemotron-3-ultra-550b-a55b@reasoning",
   "disposition": "REVIEW",
   "reason_code": "HONESTY_INCONCLUSIVE",
   "vendor": "NVIDIA",
   "model": "Nemotron 3 Ultra 550B A55B",
   "effort": "reasoning",
   "honesty_net_per_100": -0.4,
   "honesty_answers_when_unsure_pct": 29.6878,
   "honesty_confident_errors_per_100": 22.9833,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.5941,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=nvidia/nemotron-3-ultra-550b-a55b@reasoning"
  },
  {
   "id": "zai/glm-5.3@max",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "Z.ai",
   "model": "GLM-5.3",
   "effort": "max",
   "honesty_net_per_100": 14.3,
   "honesty_answers_when_unsure_pct": 29.554,
   "honesty_confident_errors_per_100": 19.55,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.8341,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=zai/glm-5.3@max"
  },
  {
   "id": "alibaba/qwen3.8-27b@xhigh",
   "disposition": "DENY",
   "reason_code": "FAILS_HONESTY",
   "vendor": "Alibaba",
   "model": "Qwen3.8 27B",
   "effort": "xhigh",
   "honesty_net_per_100": -9.9833,
   "honesty_answers_when_unsure_pct": 30.2863,
   "honesty_confident_errors_per_100": 25.5667,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.7006,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=alibaba/qwen3.8-27b@xhigh"
  },
  {
   "id": "google/gemini-3.1-pro-preview@default",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "Google",
   "model": "Gemini 3.1 Pro Preview",
   "effort": "default",
   "honesty_net_per_100": 31.88,
   "honesty_answers_when_unsure_pct": 50.8675,
   "honesty_confident_errors_per_100": 22.9667,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.8377,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=google/gemini-3.1-pro-preview@default"
  },
  {
   "id": "openai/gpt-5.6-terra@max",
   "disposition": "REVIEW",
   "reason_code": "HONESTY_INCONCLUSIVE",
   "vendor": "OpenAI",
   "model": "GPT-5.6 Terra",
   "effort": "max",
   "honesty_net_per_100": 0.05,
   "honesty_answers_when_unsure_pct": 87.8759,
   "honesty_confident_errors_per_100": 46.75,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.9007,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {
     "openai": [
      "gpt-5.6-terra"
     ],
     "zaun_gateway": [
      "openai.gpt-5.6-terra"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=openai/gpt-5.6-terra@max"
  },
  {
   "id": "alibaba/qwen3.8-2.4t-a95b@default",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "Alibaba",
   "model": "Qwen3.8 2.4T A95B",
   "effort": "default",
   "honesty_net_per_100": 4.3167,
   "honesty_answers_when_unsure_pct": 39.1758,
   "honesty_confident_errors_per_100": 26.9333,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.8238,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=alibaba/qwen3.8-2.4t-a95b@default"
  },
  {
   "id": "alibaba/qwen3.8-max@default",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "Alibaba",
   "model": "Qwen3.8 Max",
   "effort": "default",
   "honesty_net_per_100": 3.4,
   "honesty_answers_when_unsure_pct": 41.7461,
   "honesty_confident_errors_per_100": 28.45,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.8242,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=alibaba/qwen3.8-max@default"
  },
  {
   "id": "anthropic/claude-sonnet-5@max",
   "disposition": "REVIEW",
   "reason_code": "BELOW_EFFICACY",
   "vendor": "Anthropic",
   "model": "Claude Sonnet 5",
   "effort": "max",
   "honesty_net_per_100": 16.45,
   "honesty_answers_when_unsure_pct": 39.3661,
   "honesty_confident_errors_per_100": 23.6,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.8063,
   "zero_scored_evals": [],
   "match": {
    "api_ids": {
     "anthropic": [
      "claude-sonnet-5"
     ],
     "bedrock": [
      "us.anthropic.claude-sonnet-5"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=anthropic/claude-sonnet-5@max"
  },
  {
   "id": "google/gemini-3.5-flash-lite@default",
   "disposition": "DENY",
   "reason_code": "COST_UNDEFINED",
   "vendor": "Google",
   "model": "Gemini 3.5 Flash-Lite",
   "effort": "default",
   "honesty_net_per_100": 5.23,
   "honesty_answers_when_unsure_pct": 34.3573,
   "honesty_confident_errors_per_100": 24.2333,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.5552,
   "zero_scored_evals": [
    "CritPt"
   ],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=google/gemini-3.5-flash-lite@default"
  },
  {
   "id": "anthropic/claude-haiku-4.5@reasoning",
   "disposition": "DENY",
   "reason_code": "COST_UNDEFINED",
   "vendor": "Anthropic",
   "model": "Claude Haiku 4.5",
   "effort": "reasoning",
   "honesty_net_per_100": -4.37,
   "honesty_answers_when_unsure_pct": 27.3023,
   "honesty_confident_errors_per_100": 22.3833,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.4901,
   "zero_scored_evals": [
    "CritPt"
   ],
   "match": {
    "api_ids": {
     "anthropic": [
      "claude-haiku-4-5",
      "claude-haiku-4-5-20251001"
     ],
     "bedrock": [
      "us.anthropic.claude-haiku-4-5-20251001-v1:0"
     ]
    },
    "confidence": "confirmed"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=anthropic/claude-haiku-4.5@reasoning"
  },
  {
   "id": "alibaba/qwen3.8-27b@medium",
   "disposition": "DENY",
   "reason_code": "COST_UNDEFINED",
   "vendor": "Alibaba",
   "model": "Qwen3.8 27B",
   "effort": "medium",
   "honesty_net_per_100": -36.15,
   "honesty_answers_when_unsure_pct": 66.7483,
   "honesty_confident_errors_per_100": 54.5,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.56,
   "zero_scored_evals": [
    "CritPt"
   ],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=alibaba/qwen3.8-27b@medium"
  },
  {
   "id": "alibaba/qwen3.8-27b@low",
   "disposition": "DENY",
   "reason_code": "COST_UNDEFINED",
   "vendor": "Alibaba",
   "model": "Qwen3.8 27B",
   "effort": "low",
   "honesty_net_per_100": -26.6667,
   "honesty_answers_when_unsure_pct": 52.856,
   "honesty_confident_errors_per_100": 43.8,
   "honesty_standard_error": 1.291,
   "efficacy_mean": 0.5653,
   "zero_scored_evals": [
    "CritPt"
   ],
   "match": {
    "api_ids": {},
    "confidence": "unmapped"
   },
   "evidence_url": "https://zaun.ai/everyday-model-index?config=alibaba/qwen3.8-27b@low"
  }
 ]
}