Medical Knowledge Evaluation on Medbullets op4 4-option 308
92.2AccuracyClaude Opus 4.6
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude Opus 4.6Type=Commercial LLMs, Setting=BioMedArena2026.05 | 92.2 | |
| Gemini 3.1 ProType=Commercial LLMs, Setting=BioMedArena2026.05 | 91.6 | |
| Claude Sonnet 4.5Type=Commercial LLMs, Setting=BioMedArena2026.05 | 91.2 | |
| Claude Opus 4.5Type=Commercial LLMs, Setting=BioMedArena2026.05 | 90.3 | |
| Claude Opus 4.6Type=Commercial LLMs, Setting=Baseline2026.05 | 89.9 | |
| Claude Sonnet 4.6Type=Commercial LLMs, Setting=BioMedArena2026.05 | 89 | |
| Claude Sonnet 4.5Type=Commercial LLMs, Setting=Baseline2026.05 | 88.3 | |
| Claude Opus 4.5Type=Commercial LLMs, Setting=Baseline2026.05 | 87.3 | |
| Claude Sonnet 4.6Type=Commercial LLMs, Setting=Baseline2026.05 | 86 | |
| Gemini 3 FlashType=Commercial LLMs, Setting=BioMedArena2026.05 | 85.4 | |
| Gemini 3.1 ProType=Commercial LLMs, Setting=Baseline2026.05 | 70.1 | |
| Gemini 3 FlashType=Commercial LLMs, Setting=Baseline2026.05 | 64.9 | |
| SOTASource=[18]2026.05 | 62.2 |