EuroEval English Common Sense Reasoning: leaderboard
EuroEval's English common-sense reasoning task — multiple-choice questions testing everyday physical and social reasoning in English, from the EuroEval European language model benchmark suite.
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 318 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 (Non-reasoning) | 96.52 | #142 (Claude Sonnet 4.5) |
| 2 | Claude Sonnet 4.5 (Thinking) | 95.9 | #142 (Claude Sonnet 4.5) |
| 3 | Yi 1.5 34B | 94.53 | #807 |
| 4 | Qwen 3 235B A22B 2507 Instruct | 91.73 | #300 |
| 5 | Mistral Small 3.1 | 90.82 | #610 |
| 6 | Mistral Small 3 | 88.02 | #627 |
| 7 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 87.47 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 8 | Qwen 3 Next 80B A3B Instruct | 87.33 | #368 |
| 9 | Mistral Small 3.2 | 87.28 | #605 |
| 10 | Claude Sonnet 4.6 | 86.72 | #90 |
| 11 | Gemini 3 Flash (Preview) (Thinking) | 86.72 | #82 (Gemini 3 Flash (Preview)) |
| 12 | cogito-v1-preview-qwen-14B | 86.69 | |
| 13 | Llama 3.1 405B Instruct FP8 | 86.67 | #389 |
| 14 | Gemini 3 Pro (Preview) | 86.66 | #66 |
| 15 | Voxtral-Small-24B-2507 | 86.32 | #581 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-english-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.