EuroEval Polish Common Sense Reasoning — leaderboard
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. 216 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 80.96 |
| 2 | GPT-5 | 79.47 |
| 3 | Gemini 3 Pro (Preview) | 73.13 |
| 4 | GPT-5 Mini | 69.61 |
| 5 | Qwen 3 Next 80B A3B (Thinking) | 69.07 |
| 6 | Gemini 2.5 Flash (Thinking) | 68.95 |
| 7 | Gemini 2.5 Pro | 68.48 |
| 8 | Gemma 4 31B (IT) | 67.78 |
| 9 | Gemini 3 Flash (Preview) (Non-reasoning) | 65.23 |
| 10 | Claude Sonnet 4.5 (Non-reasoning) | 64.71 |
| 11 | Qwen 3 235B A22B 2507 Instruct | 64.64 |
| 12 | GPT-5.4 Mini (High) | 62.13 |
| 13 | Gemini 3.1 Flash Lite (Preview) | 61.15 |
| 14 | Qwen 3 30B A3B | 60.73 |
| 15 | Qwen 2.5 72B Instruct | 60.05 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-polish-common-sense-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.