Skip to main content

Human ratings

Medicine and healthcare (human ratings)

Among the occupational fields questions are sorted into, a category computed only from questions in medicine and healthcare.

How to read this table

  • Higher rows are rated higher. A range like “1–2” means the gap is within the margin of error.
  • The rating comes from people comparing two answers and picking the better one.
  • At a gap of 50, the higher model is picked about 57% of the time; 100 means 64%, 200 means 76%.
  • Prices are a guide per million tokens, reading then writing.
  • Length is how much text the model can read at once (tokens).

± range of the top model

RankModelDeveloperratingrating scale 1450 to 1600Week
change
OverallInput $
/1M
Output $
/1M
ContextSupportsWeightsReleasedPrice and specs
1–25Gemini 4 ArgonGoogleRating 1533 ±23−171517rank 1–3$2$101.05MGoogle Released 2026-⁠09 Week change −17 Price $2 / $10 Length 1.05M
1–27Claude Fable 5.1AnthropicRating 1527 ±17+21503rank 2–10$10$501MAnthropic Released 2026-⁠09 Week change +2 Price $10 / $50 Length 1M
1–48Muse WonderMetaRating 1524 ±29New1509rank 1–8$4$201.05MMeta Released 2026-⁠10 Price $4 / $20 Length 1.05M
1–28Claude Opus 4.7AnthropicRating 1517 ±901501rank 2–10$5$251MAnthropic Released 2026-⁠04 Price $5 / $25 Length 1M
1–28Claude Opus 4.6AnthropicRating 1516 ±8−21503rank 2–9$5$251MAnthropic Released 2026-⁠02 Week change −2 Price $5 / $25 Length 1M
1–55Claude Opus 5.5AnthropicRating 1514 ±24−11509rank 1–7$4$201MAnthropic Released 2026-⁠09 Week change −1 Price $4 / $20 Length 1M
1–39Kimi K3⁠MoonshotRating 1513 ±1301487rank 8–27$3$151.05MMoonshot Released 2026-⁠07 Price $3 / $15 Length 1.05M
1–40Claude Opus 5AnthropicRating 1512 ±13+11491rank 8–22$5$251MAnthropic Released 2026-⁠07 Week change +1 Price $5 / $25 Length 1M
1–57Muse Spark 1.2MetaRating 1512 ±23−11491rank 6–25$1.25$4.251.05MMeta Released 2026-⁠08 Week change −1 Price $1.25 / $4.25 Length 1.05M
1–44Gemini 3 ProGoogleRating 1509 ±1201486rank 10–29——1.05MGoogle Released 2025-⁠11 Price — Length 1.05M
1–48Qwen3.8 MaxAlibabaRating 1509 ±14+11483rank 10–36$2$61MAlibaba Released 2026-⁠08 Week change +1 Price $2 / $6 Length 1M
1–45Gemini 3.8 FlashGoogleRating 1508 ±12−11496rank 4–15$0.75$3.751.05MGoogle Released 2026-⁠09 Week change −1 Price $0.75 / $3.75 Length 1.05M
1–64DeepSeek-V4.1 Flash⁠DeepSeekRating 1505 ±20−21476rank 17–46——1MDeepSeek Released 2026-⁠09 Week change −2 Price — Length 1M
1–51Claude Fable 5AnthropicRating 1505 ±11−21503rank 2–9$10$501MAnthropic Released 2026-⁠06 Week change −2 Price $10 / $50 Length 1M
1–44Gemini 3.1 Pro (preview)GoogleRating 1505 ±7+11487rank 10–26$2$121.05MGoogle Released 2026-⁠02 Week change +1 Price $2 / $12 Length 1.05M
1–57Gemini 3.7 FlashGoogleRating 1503 ±14+21490rank 8–25$0.75$3.751.05MGoogle Released 2026-⁠08 Week change +2 Price $0.75 / $3.75 Length 1.05M
1–64Muse Spark 1.3MetaRating 1501 ±16+51496rank 3–15$1.25$4.251.05MMeta Released 2026-⁠09 Week change +5 Price $1.25 / $4.25 Length 1.05M
1–57Muse Spark 1.1MetaRating 1500 ±11+21490rank 8–23$1.25$4.251MMeta Released 2026-⁠07 Week change +2 Price $1.25 / $4.25 Length 1M
1–64GLM-5.3⁠Z.aiRating 1500 ±14+31481rank 11–38$1.4$4.41MZ.ai Released 2026-⁠08 Week change +3 Price $1.4 / $4.4 Length 1M
2–55Claude Opus 4.8AnthropicRating 1500 ±901481rank 12–36$5$251MAnthropic Released 2026-⁠05 Price $5 / $25 Length 1M
3–56Grok 4.1xAIRating 1500 ±1001465rank 38–53——200KxAI Released 2025-⁠11 Price — Length 200K
1–73Muse SparkMetaRating 1499 ±1901489rank 8–27———Meta Released 2026-⁠04 Price — Length —
2–64GPT-5.2 ChatOpenAIRating 1498 ±1201476rank 19–42——128KOpenAI Released 2026-⁠02 Price — Length 128K
1–66Grok 4.20 (beta1)xAIRating 1497 ±1401475rank 19–45————xAI Released — Price — Length —
5–73ERNIE 5.1BaiduRating 1492 ±1201467rank 26–53——119K—Baidu Released — Price — Length 119K
5–73GLM-5.2⁠Z.aiRating 1491 ±10+11475rank 19–43$1.4$4.41MZ.ai Released 2026-⁠06 Week change +1 Price $1.4 / $4.4 Length 1M
1–94ERNIE 5.0 (preview, 1203)BaiduRating 1491 ±23+11449rank 52–88————Baidu Released — Week change +1 Price — Length —
1–125MiMo-V2.6 Pro⁠XiaomiRating 1491 ±37+81480rank 10–44$0.435$0.871.05MXiaomi Released 2026-⁠09 Week change +8 Price $0.435 / $0.87 Length 1.05M
5–73GLM-5.3 Flash⁠Z.aiRating 1490 ±12−11476rank 19–43$0.15$0.51MZ.ai Released 2026-⁠08 Week change −1 Price $0.15 / $0.5 Length 1M
7–73Dola Seed 2.0 ProByteDanceRating 1490 ±901456rank 48–71——131.1K—ByteDance Released — Price — Length 131.1K
5–79Qwen3.5 Max (preview)AlibabaRating 1490 ±1501465rank 36–60————Alibaba Released — Price — Length —
9–73Claude Sonnet 4.6AnthropicRating 1488 ±901472rank 24–49$3$151MAnthropic Released 2026-⁠02 Price $3 / $15 Length 1M
6–78Claude Opus 4.5AnthropicRating 1488 ±1201474rank 23–46$5$25200KAnthropic Released 2025-⁠11 Price $5 / $25 Length 200K
5–84GPT-5.5 InstantOpenAIRating 1487 ±14+11473rank 20–50———OpenAI Released 2026-⁠05 Week change +1 Price — Length —
7–75Gemini 3.5 FlashGoogleRating 1487 ±1101477rank 18–41$1.5$91.05MGoogle Released 2026-⁠05 Price $1.5 / $9 Length 1.05M
5–96GLM-4.7⁠Z.aiRating 1487 ±2001441rank 65–102$0.6$2.2204.8KZ.ai Released 2025-⁠12 Price $0.6 / $2.2 Length 204.8K
10–74Grok 4.20 Beta Reasoning (0309)xAIRating 1487 ±901472rank 24–50——2M—xAI Released — Price — Length 2M
10–74GPT-5.5OpenAIRating 1487 ±9+11482rank 12–36$5$301.05MOpenAI Released 2026-⁠04 Week change +1 Price $5 / $30 Length 1.05M
1–124Qwen3.6 Max (preview)AlibabaRating 1486 ±32+31461rank 36–72$1.3$7.8240KAlibaba Released 2026-⁠04 Week change +3 Price $1.3 / $7.8 Length 240K
10–78DeepSeek-V4 Pro (preview)⁠DeepSeekRating 1485 ±1001455rank 49–72————DeepSeek Released — Price — Length —
How to read this page
  • These ratings exclude the effect of response length and formatting. Differences where the ± ranges overlap are within the margin of error, so about the same.
  • In the Supports column the icons are, from left: can use tools / can read images / can answer in a fixed format (JSON); faded means not supported or unknown.
  • Open-weights models have their contents (the weights) published, so you can also run them on your own computer or server. Models without the open-weights mark are normally used through the developer's own services (apps or API); for some models the weights status is unknown.
  • Names such as ChatGPT next to a model are the consumer services its developer offers. Check on the service itself whether that model is available there.

Data: Arena, Epoch AI, Swallow LLM team (CC BY 4.0), Models.dev (MIT), updated 2026-⁠10-⁠24, data sources