Polish Knowledge Benchmark - Medicine & Health: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 68 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 397B A17B | 91.54 |
| 2 | Gemini 3 Flash (Preview) | 91.11 |
| 3 | Gemini 3.1 Flash Lite (Preview) | 90.67 |
| 4 | Gemini 3.1 Flash Lite | 90.24 |
| 5 | Gemini 2.5 Flash | 89.59 |
| 6 | Gemini 3.6 Flash | 89.37 |
| 7 | DeepSeek V4 Flash | 88.94 |
| 8 | Gemini 3.5 Flash Lite | 88.72 |
| 9 | Gemma 4 31B (IT) | 88.29 |
| 10 | Grok 4.1 Fast | 88.29 |
| 11 | Gemini 2.0 Flash (001) | 88.07 |
| 12 | Mistral Large 3 | 86.55 |
| 13 | Mistral Medium 3.1 | 86.55 |
| 14 | Gemma 4 26B A4B (IT) | 86.12 |
| 15 | DeepSeek V3.2 | 85.9 |
Interactive version: theaggregate.ai/benchmark?slug=polish-knowledge-benchmark-medicine-health · How It Works · Data refreshed daily, snapshot 2026-09-19.