跳过主要内容
评测来源/MedCode
观察中专业工作

MedCode

Vals AI · MedCode 的公开模型评测结果。

官方评测
来源说明

该来源测量模型在「专业工作」领域的具体交付表现,原始成绩会和统一能力读数分开展示。

限制: 不同版本、推理设置和测试集可能导致分数变化,请结合数据时间阅读。

使用方式

参与排名的来源会影响能力分;参考、交叉参考和观察来源仅用于对比与核验。

本来源的模型成绩

Claude Opus 563.5763.62026-11-05
Gemini 4 Argon58.858.82026-11-05
Claude Fable 556.0756.12026-11-05
Claude Opus 4.754.8654.92026-11-05
Claude Fable 5.153.5153.52026-11-05
Claude Opus 4.853.2253.22026-11-05
Gemini 3.6 Flash53.1553.12026-11-05
Claude Sonnet 5.552.9252.92026-11-05
Claude Haiku 5.551.5451.52026-11-05
Gemini 2.5 Pro50.5950.62026-11-05
Claude Opus 5.549.849.82026-11-05
GPT-5.249.7549.82026-11-05
GPT-549.6349.62026-11-05
Grok 4.749.5549.52026-11-05
Kimi K349.3649.42026-11-05
Muse Spark 1.249.3549.42026-11-05
Claude Opus 4.549.1649.22026-11-05
Claude Opus 4.649.1349.12026-11-05
GPT-5.549.149.12026-11-05
GPT-6.1 Sol48.8448.82026-11-05
GPT-6 Astra48.4948.52026-11-05
Gemini 3.8 Flash48.1348.12026-11-05
Gemini 3.1 Flash Lite Preview47.647.62026-11-05
Claude Sonnet 547.5447.52026-11-05
o347.2947.32026-11-05
GPT-6 Sol47.0747.12026-11-05
MiniMax-M346.2946.32026-11-05
MiMo V2.6 Pro44.9745.02026-11-05
Grok 4.644.7144.72026-11-05
GPT-6 Luna44.6944.72026-11-05
Claude Sonnet 4.544.1344.12026-11-05
GPT-5.6 Sol43.9744.02026-11-05
Gemini 3.5 Flash Lite43.4943.52026-11-05
GPT-5.6 Terra43.4143.42026-11-05
Grok 4.543.2943.32026-11-05
GPT-5 mini43.0543.02026-11-05
GLM 5.342.8642.92026-11-05
DeepSeek V4 Pro 081342.4742.52026-11-05
GPT-5.6 Luna42.3942.42026-11-05
GLM-5.141.641.62026-11-05
DeepSeek V4 Flash 073141.4141.42026-11-05
GPT-5.441.2941.32026-11-05
Inkling41.1941.22026-11-05
DeepSeek V4.1 Flash41.1741.22026-11-05
MiMo V2.6 Flash41.0641.12026-11-05
GLM-5.240.7740.82026-11-05
Mistral Large 440.6940.72026-10-22
Qwen3.8 Max40.6740.72026-11-05
Kimi K2.640.1440.12026-11-05
Kimi K2.539.3239.32026-11-05
Qwen3.7 Max38.7538.82026-11-05
Grok 4.338.0738.12026-11-05
Inkling Small37.8937.92026-11-05
Qwen3.6 Plus36.8936.92026-11-05
Llama 4 Maverick36.5136.52026-11-05
MiniMax-M2.734.4434.42026-11-05
MiniMax-M2.134.0834.12026-11-05
o4-mini33.7933.82026-11-05
Qwen3.5-Flash3333.02026-11-05
GLM-4.732.7732.82026-11-05
Claude Haiku 4.532.6832.72026-11-05
MiMo-V2.5-Pro32.4832.52026-11-05
Ling-3.0-flash (free)32.2732.32026-11-05
Grok 4.20 (Reasoning)32.1632.22026-11-05
MiMo-V2.531.8931.92026-11-05
Qwen3-VL Plus31.6531.62026-11-05
Qwen3 Max Thinking31.3731.42026-11-05
GPT-5 nano30.4430.42026-11-05
Llama 4 Scout23.3123.32026-11-05
Laguna M.123.1123.12026-11-05
Laguna XS.221.2521.32026-11-05
Command A Plus19.7219.72026-11-05

常见问题