Galileo Agent - Healthcare Accuracy — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 | 62 |
| 2 | Claude Sonnet 4 (20250514) | 62 |
| 3 | Qwen 2.5 72B Instruct | 61 |
| 4 | GPT-4.1 Mini | 60 |
| 5 | Mistral Medium 3.1 | 60 |
| 6 | Gemini 2.5 Flash Lite | 60 |
| 7 | Kimi K2 | 49 |
| 8 | Qwen 3 235B A22B 2507 Instruct | 49 |
| 9 | Gemini 2.5 Pro | 40 |
| 10 | GPT-4.1 Nano | 40 |
| 11 | Grok 4 | 40 |
| 12 | GLM 4.5 Air | 40 |
| 13 | Gemini 2.5 Flash | 38 |
| 14 | Magistral Medium | 35 |
| 15 | DeepSeek V3 | 32 |
Interactive version: theaggregate.ai/benchmark?slug=galileo-agent-healthcare-accuracy · How the rankings work · Data refreshed daily, snapshot 2026-07-22.