BRIDGE Medical Leaderboard - Few-Shot: leaderboard
Metric: Average Performance (%). Source: huggingface.co. 109 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.8 27B (Non-reasoning) | 55.67 |
| 2 | Gemini 1.5 Pro (002) | 55.51 |
| 3 | Gemma 4 31B (IT) | 54.88 |
| 4 | Gemini 2.5 Flash | 53.36 |
| 5 | Gemini 2.0 Flash (001) | 53.33 |
| 6 | Gemma 4 26B A4B (IT) | 53.22 |
| 7 | GPT-4o (2024-08-06) | 52.59 |
| 8 | DeepSeek R1 | 51.38 |
| 9 | Qwen 2.5 72B Instruct | 50.99 |
| 10 | Qwen 3 Next 80B A3B (Thinking) | 50.9 |
| 11 | Mistral Large 2 (Nov) Instruct (2411) | 50.68 |
| 12 | Athene-V2-Chat | 50.68 |
| 13 | Qwen 3 Next 80B A3B Instruct | 50.56 |
| 14 | Llama 3.1 70B Instruct | 50.52 |
| 15 | Qwen 3 30B A3B 2507 (Thinking) | 50.26 |
Interactive version: theaggregate.ai/benchmark?slug=bridge-medical-leaderboard-few-shot · How It Works · Data refreshed daily, snapshot 2026-09-05.