EuroEval Polish: leaderboard
Polish-language EuroEval all-task suite spanning NLU, knowledge, common-sense reasoning, reading comprehension, summarization, and related tasks.
Metric: Average Score (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 241 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 71.84 | #98 |
| 2 | Gemini 2.5 Flash (Thinking) | 68.33 | #245 (Gemini 2.5 Flash) |
| 3 | Gemini 2.5 Pro | 68.03 | #152 |
| 4 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 67.34 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 5 | Gemini 3 Pro (Preview) | 64.78 | #66 |
| 6 | Qwen 3 235B A22B 2507 Instruct | 63.9 | #300 |
| 7 | Claude Sonnet 4.5 (Thinking) | 63.83 | #142 (Claude Sonnet 4.5) |
| 8 | GPT-5.4 Mini (2026-03-17) (High) | 62.52 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 9 | Gemini 3 Flash (Preview) (Non-reasoning) | 62.28 | #82 (Gemini 3 Flash (Preview)) |
| 10 | Gemma 4 31B (IT) | 61.64 | #176 |
| 11 | Gemini 3 Flash (Preview) (Thinking) | 61.59 | #82 (Gemini 3 Flash (Preview)) |
| 12 | Qwen 3 Next 80B A3B (Thinking) | 61.4 | #320 (Qwen 3 Next 80B A3B) |
| 13 | Gemini 3.1 Flash Lite (Preview) | 61.02 | #194 |
| 14 | Qwen 3 30B A3B | 60.61 | #493 |
| 15 | Qwen 3 14B | 60.48 | #537 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-polish · How It Works · Data refreshed daily, snapshot 2026-10-20.