List your company

Medical Question Answering on HealthBench Hard 1000

86AccuracyClaude Sonnet 4.6
58.64865.74972.8579.951May 7, 2026

Evaluation results

MethodLinks
Claude Sonnet 4.6Type=Commercial LLMs, Setting=BioMedArena2026.0586
Gemini 3.1 ProType=Commercial LLMs, Setting=BioMedArena2026.0580.8
Gemini 3 FlashType=Commercial LLMs, Setting=BioMedArena2026.0580.7
Claude Opus 4.6Type=Commercial LLMs, Setting=BioMedArena2026.0580.2
Claude Opus 4.5Type=Commercial LLMs, Setting=BioMedArena2026.0578.9
Claude Opus 4.6Type=Commercial LLMs, Setting=Baseline2026.0576.2
Claude Sonnet 4.5Type=Commercial LLMs, Setting=BioMedArena2026.0575.3
Claude Opus 4.5Type=Commercial LLMs, Setting=Baseline2026.0572.5
Gemini 3.1 ProType=Commercial LLMs, Setting=Baseline2026.0572
Claude Sonnet 4.6Type=Commercial LLMs, Setting=Baseline2026.0569.3
Claude Sonnet 4.5Type=Commercial LLMs, Setting=Baseline2026.0567.9
Gemini 3 FlashType=Commercial LLMs, Setting=Baseline2026.0559.7