Clinical End-to-End Performance on Translational medicine scenario family 30 queries
74.7Positive RateBIORESEARCHER
Evaluation results
| Method | Links | ||
|---|---|---|---|
| BIORESEARCHERcore model=GPT-5.4, reasoning effort=medium2026.05 | 74.7 | 96.8 | |
| OpenAI Deep Research2026.05 | 68.9 | 81.1 | |
| CellTypecore model=Claude Opus 4.72026.05 | 61.7 | 83.3 | |
| Medeacore model=GPT-5.4, reasoning effort=low2026.05 | 33.7 | 93.3 |