Share your thoughts, 1 month free Claude Pro on usSee more

Medical and Health Knowledge on HealthBench

37.2Accuracy

GLM-4.7 & ANDES (Ours)

Updated 1d ago

Evaluation Results

Method	Links
GLM-4.7 & ANDES (Ours) 2026.05		37.2
Official Instruct Model 2026.05		29.58
GPT-5.2 2026.05		21.92
Opus-4.6 (1M) 2026.05		21.12
Opus-4.6 2026.05		18.81
GPT-5.4 (High) 2026.05		18.64
Gemini-3.1-Pro 2026.05		18.45
Opus-4.7 (xHigh) 2026.05		16.53
GLM-4.7 (Scaffold-only) 2026.05		7.38
Base Model (SmolLM3-3B) 2026.05		0
Sonnet-4.5 2026.05		0
Qwen3-Max 2026.05		0
Kimi-K2-Thinking 2026.05		0
MiniMax-M2.1 2026.05		0
GPT-5.1-Codex-Max 2026.05		0
MiniMax-M2.5 2026.05		0
GLM-4.7 (OpenCode) 2026.05		0