EuroEval Polish — leaderboard
Metric: Average Score (%). Source: euroeval.com. 241 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 71.84 |
| 2 | Gemini 2.5 Flash (Thinking) | 68.33 |
| 3 | Gemini 2.5 Pro | 68.03 |
| 4 | Gemini 3 Pro (Preview) | 64.78 |
| 5 | Qwen 3 235B A22B 2507 Instruct | 63.9 |
| 6 | Claude Sonnet 4.5 (Thinking) | 63.83 |
| 7 | GPT-5.4 Mini (High) | 62.52 |
| 8 | Gemini 3 Flash (Preview) (Non-reasoning) | 62.28 |
| 9 | Gemma 4 31B (IT) | 61.64 |
| 10 | Qwen 3 Next 80B A3B (Thinking) | 61.4 |
| 11 | Gemini 3.1 Flash Lite (Preview) | 61.02 |
| 12 | Qwen 3 30B A3B | 60.61 |
| 13 | Qwen 3 14B | 60.48 |
| 14 | GPT-5.4 Mini (Medium) | 60.22 |
| 15 | Claude Sonnet 4.6 | 59.88 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-polish · How the rankings work · Data refreshed daily, snapshot 2026-07-22.