BioTool - NCBI: 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 476 NCBI queries of the test split). Source: arxiv.org. Saturation forecast: Around 2029. 12 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.579.8
2Gemini 3 Pro72.5
3Qwen 3 4B 2507 Instruct53.4
4Qwen 2.5 7B Instruct48
5Llama 3.1 8B Instruct28.4
6Qwen 3 8B26.2
7GPT-5.115.5
8GPT-5.1 Codex14.8

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