{
  "schemaVersion": 1,
  "retrievedAt": "2026-09-11T10:12:59.325Z",
  "license": "CC BY 4.0",
  "canonicalPage": "https://llm-stats.com/leaderboards/best-ai-for-healthcare",
  "methodologyUrl": "https://llm-stats.com/research/best-ai-for-healthcare/methodology.md",
  "evidenceClass": "healthcare-category aggregation of published benchmark records",
  "scope": "Underlying AI model evidence; not healthcare products, diagnoses, clinical validation, patient outcomes, regulatory status, or medical advice",
  "modelCount": 244,
  "benchmarkCount": 41,
  "limitations": [
    "A category score is not a percentage of clinical accuracy.",
    "Benchmark evidence does not establish safety, efficacy, regulatory status, or improved patient outcomes.",
    "Product interfaces, retrieval, guardrails, tools, prompts, and model versions can change behavior.",
    "Representative local validation and qualified clinical review are required for healthcare use."
  ],
  "records": [
    {
      "rank": 1,
      "modelId": "qwen3.7-max",
      "model": "Qwen3.7 Max",
      "organization": "Alibaba Cloud / Qwen Team",
      "healthcareCategoryScore": 44.82,
      "inputUsdPerMillionTokens": 1.25,
      "outputUsdPerMillionTokens": 3.75,
      "contextTokens": 1000000,
      "license": "proprietary"
    },
    {
      "rank": 2,
      "modelId": "qwen3.7-plus",
      "model": "Qwen3.7-Plus",
      "organization": "Alibaba Cloud / Qwen Team",
      "healthcareCategoryScore": 42.1,
      "inputUsdPerMillionTokens": null,
      "outputUsdPerMillionTokens": null,
      "contextTokens": null,
      "license": "proprietary"
    },
    {
      "rank": 3,
      "modelId": "qwen3.6-plus",
      "model": "Qwen3.6 Plus",
      "organization": "Alibaba Cloud / Qwen Team",
      "healthcareCategoryScore": 42,
      "inputUsdPerMillionTokens": 0.5,
      "outputUsdPerMillionTokens": 3,
      "contextTokens": 1000000,
      "license": "proprietary"
    },
    {
      "rank": 4,
      "modelId": "qwen3.5-397b-a17b",
      "model": "Qwen3.5-397B-A17B",
      "organization": "Alibaba Cloud / Qwen Team",
      "healthcareCategoryScore": 39.17,
      "inputUsdPerMillionTokens": 0.45,
      "outputUsdPerMillionTokens": 3,
      "contextTokens": 262144,
      "license": "apache_2_0"
    },
    {
      "rank": 5,
      "modelId": "qwen3.5-122b-a10b",
      "model": "Qwen3.5-122B-A10B",
      "organization": "Alibaba Cloud / Qwen Team",
      "healthcareCategoryScore": 38.18,
      "inputUsdPerMillionTokens": 0.29,
      "outputUsdPerMillionTokens": 2.4,
      "contextTokens": 262144,
      "license": "apache_2_0"
    },
    {
      "rank": 6,
      "modelId": "muse-spark",
      "model": "Muse Spark",
      "organization": "Meta",
      "healthcareCategoryScore": 36.77,
      "inputUsdPerMillionTokens": null,
      "outputUsdPerMillionTokens": null,
      "contextTokens": null,
      "license": "proprietary"
    },
    {
      "rank": 7,
      "modelId": "sakana-namazu",
      "model": "Sakana Namazu",
      "organization": "Sakana AI",
      "healthcareCategoryScore": 36.34,
      "inputUsdPerMillionTokens": 0.95,
      "outputUsdPerMillionTokens": 4,
      "contextTokens": 256000,
      "license": "proprietary"
    },
    {
      "rank": 8,
      "modelId": "kimi-k2.5",
      "model": "Kimi K2.5",
      "organization": "Moonshot AI",
      "healthcareCategoryScore": 36.18,
      "inputUsdPerMillionTokens": null,
      "outputUsdPerMillionTokens": null,
      "contextTokens": null,
      "license": "mit"
    }
  ]
}