EuroEval Polish Common Sense Reasoning: leaderboard
EuroEval's Polish common-sense reasoning task — multiple-choice questions testing everyday physical and social reasoning in Polish, from the EuroEval European language model benchmark suite.
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. Saturation forecast: Around May 2027. 216 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 80.96 | #142 (Claude Sonnet 4.5) |
| 2 | GPT-5 | 79.47 | #98 |
| 3 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 74.08 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 4 | Gemini 3 Pro (Preview) | 73.13 | #66 |
| 5 | GPT-5 Mini (2025-08-07) | 69.61 | #172 |
| 6 | Qwen 3 Next 80B A3B (Thinking) | 69.07 | #320 (Qwen 3 Next 80B A3B) |
| 7 | Gemini 2.5 Flash (Thinking) | 68.95 | #245 (Gemini 2.5 Flash) |
| 8 | Gemini 2.5 Pro | 68.48 | #152 |
| 9 | Gemma 4 31B (IT) | 67.78 | #176 |
| 10 | Gemini 3 Flash (Preview) (Non-reasoning) | 65.23 | #82 (Gemini 3 Flash (Preview)) |
| 11 | Gemini 3 Flash (Preview) (Thinking) | 64.78 | #82 (Gemini 3 Flash (Preview)) |
| 12 | Claude Sonnet 4.5 (Non-reasoning) | 64.71 | #142 (Claude Sonnet 4.5) |
| 13 | Qwen 3 235B A22B 2507 Instruct | 64.64 | #300 |
| 14 | GPT-5.4 Mini (2026-03-17) (High) | 62.13 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 15 | Gemini 3.1 Flash Lite (Preview) | 61.15 | #194 |
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-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.