List your company
ResearchFormerly WizWand

Medical and Health Knowledge on HealthBench

37.2AccuracyGLM-4.7 & ANDES (Ours)
-1.4888.55618.628.644May 31, 2026
Updated 5mo ago

Evaluation results

MethodLinks
GLM-4.7 & ANDES (Ours)Protocol=Proposed Method, Backbone=SmolLM3-3B2026.0537.2
Official Instruct ModelProtocol=Official Instruct, Backbone=SmolLM3-3B2026.0529.58
GPT-5.2Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.0521.92
Opus-4.6 (1M)Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.0521.12
Opus-4.6Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.0518.81
GPT-5.4 (High)Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.0518.64
Gemini-3.1-ProProtocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.0518.45
Opus-4.7 (xHigh)Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.0516.53
GLM-4.7 (Scaffold-only)Protocol=Proposed Method, Backbone=SmolLM3-3B2026.057.38
Base Model (SmolLM3-3B)Protocol=Zero-Shot, Backbone=SmolLM3-3B2026.050
Sonnet-4.5Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.050
Qwen3-MaxProtocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.050
Kimi-K2-ThinkingProtocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.050
MiniMax-M2.1Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.050
GPT-5.1-Codex-MaxProtocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.050
MiniMax-M2.5Protocol=Agent-Post-Trained, Backbone=SmolLM3-3B2026.050
GLM-4.7 (OpenCode)Protocol=Proposed Method, Backbone=SmolLM3-3B2026.050