Biomedical Intelligence Evaluation on BixBench 205 (Evaluation)
85.9AccuracyGemini 3.1 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 3.1 ProType=Commercial LLMs, Setting=BioMedArena2026.05 | 85.9 | |
| Gemini 3 FlashType=Commercial LLMs, Setting=BioMedArena2026.05 | 69.3 | |
| Claude Opus 4.6Type=Commercial LLMs, Setting=BioMedArena2026.05 | 53.7 | |
| Claude Opus 4.5Type=Commercial LLMs, Setting=BioMedArena2026.05 | 50.2 | |
| GPT-5.4Type=Commercial LLMs, Setting=BioMedArena2026.05 | 49.8 | |
| Claude Sonnet 4.6Type=Commercial LLMs, Setting=BioMedArena2026.05 | 48.3 | |
| Gemini 3.1 ProType=Commercial LLMs, Setting=Baseline2026.05 | 42.4 | |
| Claude Sonnet 4.5Type=Commercial LLMs, Setting=BioMedArena2026.05 | 42.4 | |
| Claude Opus 4.6Type=Commercial LLMs, Setting=Baseline2026.05 | 42 | |
| Claude Opus 4.5Type=Commercial LLMs, Setting=Baseline2026.05 | 41 | |
| Claude Sonnet 4.6Type=Commercial LLMs, Setting=Baseline2026.05 | 40.5 | |
| GPT-5.4Type=Commercial LLMs, Setting=Baseline2026.05 | 40 | |
| SOTASource=[31]2026.05 | 38.5 | |
| Gemini 3 FlashType=Commercial LLMs, Setting=Baseline2026.05 | 38.5 | |
| Qwen3-235BType=Public LLMs, Setting=BioMedArena2026.05 | 35.1 | |
| GLM-4.5Type=Public LLMs, Setting=BioMedArena2026.05 | 30.2 | |
| Trinity-LargeType=Public LLMs, Setting=BioMedArena2026.05 | 26.3 | |
| GLM-4.5Type=Public LLMs, Setting=Baseline2026.05 | 23.9 | |
| Qwen3-235BType=Public LLMs, Setting=Baseline2026.05 | 22.4 | |
| INTELLECT-3.1Type=Public LLMs, Setting=BioMedArena2026.05 | 20 | |
| Claude Sonnet 4.5Type=Commercial LLMs, Setting=Baseline2026.05 | 17.1 | |
| Nemotron-3 Super 120BType=Public LLMs, Setting=Baseline2026.05 | 13.2 | |
| Nemotron-3 Super 120BType=Public LLMs, Setting=BioMedArena2026.05 | 10.7 | |
| Trinity-LargeType=Public LLMs, Setting=Baseline2026.05 | 5.4 | |
| INTELLECT-3.1Type=Public LLMs, Setting=Baseline2026.05 | 5.4 |