BioTool: 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; 1,408 test queries over NCBI, UniProt and Ensembl). Source: arxiv.org. Saturation forecast: Around December 2027. 12 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.581.4
2Gemini 3 Pro79.2
3Qwen 2.5 7B Instruct64
4Qwen 3 4B 2507 Instruct63.1
5GPT-5.1 Codex56.3
6GPT-5.155.4
7Llama 3.1 8B Instruct54.8
8Qwen 3 8B54.1

Interactive version: theaggregate.ai/benchmark?slug=biotool · How It Works · Data refreshed daily, snapshot 2026-09-25.