List your company
ResearchFormerly WizWand

Health Dialogue on HealthBench

44.92AccuracyOfficial Instruct Model
-1.796810.331622.4634.5884May 31, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Official Instruct ModelEvaluation Category=Official Instruct Model2026.0544.92
GPT-5.4 (High)Evaluation Category=Agent-Post-Trained, Base Model=Qwen3-1.7B2026.0529.39
GLM-4.7 & ANDESEvaluation Category=Proposed Method Comparison, Base Model=Qwen3-1.7B2026.0525.87
GLM-4.7 (Scaffold-only)Evaluation Category=Proposed Method Comparison, Base Model=Qwen3-1.7B2026.0516.74
Opus-4.7 (xHigh)Evaluation Category=Agent-Post-Trained, Base Model=Qwen3-1.7B2026.0516.23
Gemini-3.1-ProEvaluation Category=Agent-Post-Trained, Base Model=Qwen3-1.7B2026.0510.93
Opus-4.6 (1M)Evaluation Category=Agent-Post-Trained, Base Model=Qwen3-1.7B2026.059.73
GPT-5.2Evaluation Category=Agent-Post-Trained, Base Model=Qwen3-1.7B2026.059.33
Opus-4.6Evaluation Category=Agent-Post-Trained, Base Model=Qwen3-1.7B2026.058.58
MiniMax-M2.5Evaluation Category=Agent-Post-Trained, Base Model=Qwen3-1.7B2026.057.66
Base Model (Qwen3-1.7B)Evaluation Category=Zero-Shot2026.057.54
MiniMax-M2.1Evaluation Category=Agent-Post-Trained, Base Model=Qwen3-1.7B2026.057.54
Qwen3-MaxEvaluation Category=Agent-Post-Trained, Base Model=Qwen3-1.7B2026.057.54
Kimi-K2-ThinkingEvaluation Category=Agent-Post-Trained, Base Model=Qwen3-1.7B2026.057.54
GPT-5.1-Codex-MaxEvaluation Category=Agent-Post-Trained, Base Model=Qwen3-1.7B2026.057.54
GLM-4.7 (OpenCode)Evaluation Category=Proposed Method Comparison, Base Model=Qwen3-1.7B2026.057.54
Sonnet-4.5Evaluation Category=Agent-Post-Trained, Base Model=Qwen3-1.7B2026.050