EuroEval Italian Common Sense Reasoning: leaderboard
EuroEval's Italian common-sense reasoning task — multiple-choice questions testing everyday physical and social reasoning in Italian, from the EuroEval European language model benchmark suite.
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. Saturation forecast: Around June 2027. 395 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 (Non-reasoning) | 91.54 | #142 (Claude Sonnet 4.5) |
| 2 | Qwen 3 235B A22B 2507 Instruct | 86.12 | #300 |
| 3 | Claude Sonnet 4.5 (Thinking) | 86.03 | #142 (Claude Sonnet 4.5) |
| 4 | Mistral Small 3.1 | 84.87 | #610 |
| 5 | Mistral Small 3 | 82.73 | #627 |
| 6 | Gemini 3 Flash (Preview) (Non-reasoning) | 82.73 | #82 (Gemini 3 Flash (Preview)) |
| 7 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 82.33 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 8 | Gemini 3 Flash (Preview) (Thinking) | 82.22 | #82 (Gemini 3 Flash (Preview)) |
| 9 | Gemini 3 Pro (Preview) | 81.22 | #66 |
| 10 | Claude Sonnet 4.6 | 80.69 | #90 |
| 11 | Qwen 3 Next 80B A3B Instruct | 79.82 | #368 |
| 12 | Llama 3.1 405B Instruct FP8 | 79.65 | #389 |
| 13 | Gemini 2.5 Pro | 78.72 | #152 |
| 14 | Mistral Small 3.2 | 78.39 | #605 |
| 15 | Qwen 3 Next 80B A3B (Thinking) | 78.31 | #320 (Qwen 3 Next 80B A3B) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-italian-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.