BRIDGE Medical Leaderboard — leaderboard
Clinical practice text understanding leaderboard for medical LLMs, covering summarization, dialogue, clinical evidence, and EHR-oriented tasks across multiple prompting settings.
Metric: Average Performance (%). Source: huggingface.co. Status: saturation imminent. 107 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 4 31B (IT) | 49.17 |
| 2 | Gemma 4 26B A4B (IT) | 47.63 |
| 3 | Gemini 2.5 Flash | 47.16 |
| 4 | Gemini 1.5 Pro (002) | 46.63 |
| 5 | Gemini 2.0 Flash (001) | 46.11 |
| 6 | DeepSeek R1 | 45.91 |
| 7 | Qwen 3 Next 80B A3B (Thinking) | 45.89 |
| 8 | Qwen 3 30B A3B 2507 (Thinking) | 44.5 |
| 9 | Mistral Large 2 (Nov) Instruct (2411) | 43.95 |
| 10 | Athene-V2-Chat | 43.9 |
| 11 | Qwen 2.5 72B Instruct | 43.82 |
| 12 | Qwen 3 Next 80B A3B Instruct | 43.62 |
| 13 | Qwen 3 235B A22B (Thinking) | 43.29 |
| 14 | Qwen 3 30B A3B (Thinking) | 42.43 |
| 15 | Qwen 2.5 32B Instruct | 42.36 |
Interactive version: theaggregate.ai/benchmark?slug=bridge-medical-leaderboard · How the rankings work · Data refreshed daily, snapshot 2026-07-22.