List your company

Biomedical Intelligence Evaluation on BixBench 205 (Evaluation)

85.9AccuracyGemini 3.1 Pro
2.1823.91545.6567.385May 7, 2026

Evaluation results

MethodLinks
Gemini 3.1 ProType=Commercial LLMs, Setting=BioMedArena2026.0585.9
Gemini 3 FlashType=Commercial LLMs, Setting=BioMedArena2026.0569.3
Claude Opus 4.6Type=Commercial LLMs, Setting=BioMedArena2026.0553.7
Claude Opus 4.5Type=Commercial LLMs, Setting=BioMedArena2026.0550.2
GPT-5.4Type=Commercial LLMs, Setting=BioMedArena2026.0549.8
Claude Sonnet 4.6Type=Commercial LLMs, Setting=BioMedArena2026.0548.3
Gemini 3.1 ProType=Commercial LLMs, Setting=Baseline2026.0542.4
Claude Sonnet 4.5Type=Commercial LLMs, Setting=BioMedArena2026.0542.4
Claude Opus 4.6Type=Commercial LLMs, Setting=Baseline2026.0542
Claude Opus 4.5Type=Commercial LLMs, Setting=Baseline2026.0541
Claude Sonnet 4.6Type=Commercial LLMs, Setting=Baseline2026.0540.5
GPT-5.4Type=Commercial LLMs, Setting=Baseline2026.0540
SOTASource=[31]2026.0538.5
Gemini 3 FlashType=Commercial LLMs, Setting=Baseline2026.0538.5
Qwen3-235BType=Public LLMs, Setting=BioMedArena2026.0535.1
GLM-4.5Type=Public LLMs, Setting=BioMedArena2026.0530.2
Trinity-LargeType=Public LLMs, Setting=BioMedArena2026.0526.3
GLM-4.5Type=Public LLMs, Setting=Baseline2026.0523.9
Qwen3-235BType=Public LLMs, Setting=Baseline2026.0522.4
INTELLECT-3.1Type=Public LLMs, Setting=BioMedArena2026.0520
Claude Sonnet 4.5Type=Commercial LLMs, Setting=Baseline2026.0517.1
Nemotron-3 Super 120BType=Public LLMs, Setting=Baseline2026.0513.2
Nemotron-3 Super 120BType=Public LLMs, Setting=BioMedArena2026.0510.7
Trinity-LargeType=Public LLMs, Setting=Baseline2026.055.4
INTELLECT-3.1Type=Public LLMs, Setting=Baseline2026.055.4