List your company

Chemical Reasoning on SuperChem 500 (Total)

72.8Accuracy (Text)Claude Opus 4.6
27.35239.15150.9562.749May 7, 2026

Evaluation results

MethodLinks
Claude Opus 4.6Type=Commercial LLMs, Setting=BioMedArena2026.0572.857.965.8
GPT-5.4Type=Commercial LLMs, Setting=BioMedArena2026.0566.858.362.8
Claude Sonnet 4.6Type=Commercial LLMs, Setting=BioMedArena2026.056653.658.6
Claude Opus 4.6Type=Commercial LLMs, Setting=Baseline2026.0562.330.247.2
Claude Opus 4.5Type=Commercial LLMs, Setting=BioMedArena2026.0559.241.350.8
GPT-5.4Type=Commercial LLMs, Setting=Baseline2026.0557.722.641.2
SOTASource=[23], [25]2026.0557.563.2—
Gemini 3.1 ProType=Commercial LLMs, Setting=BioMedArena2026.0557.462.659.8
Gemini 3.1 ProType=Commercial LLMs, Setting=Baseline2026.0554.319.237.8
Gemini 3 FlashType=Commercial LLMs, Setting=BioMedArena2026.055434.544.8
Gemini 3 FlashType=Commercial LLMs, Setting=Baseline2026.0549.110.230.8
Claude Opus 4.5Type=Commercial LLMs, Setting=Baseline2026.0548.324.337
Claude Sonnet 4.6Type=Commercial LLMs, Setting=Baseline2026.0540.424.733
Claude Sonnet 4.5Type=Commercial LLMs, Setting=BioMedArena2026.0539.631.935.4
Claude Sonnet 4.5Type=Commercial LLMs, Setting=Baseline2026.0529.117.423.6