BioTool - UniProt: leaderboard
Metric: BioTool score (%; mean MedCPT embedding similarity between the observation returned by the model's API call and the reference observation, 0 for a failed call; the 471 UniProt queries of the test split). Source: arxiv.org. Saturation forecast: Around December 2026. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 87.8 |
| 2 | Claude Sonnet 4.5 | 87.3 |
| 3 | GPT-5.1 Codex | 80.5 |
| 4 | Qwen 2.5 7B Instruct | 79 |
| 5 | GPT-5.1 | 78.7 |
| 6 | Llama 3.1 8B Instruct | 77.5 |
| 7 | Qwen 3 8B | 73.1 |
| 8 | Qwen 3 4B 2507 Instruct | 71.9 |
Interactive version: theaggregate.ai/benchmark?slug=biotool-uniprot · How It Works · Data refreshed daily, snapshot 2026-09-25.