EuroEval Italian Common Sense Reasoning: leaderboard
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. 395 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Non-reasoning) | 91.54 |
| 2 | Qwen 3 235B A22B 2507 Instruct | 86.12 |
| 3 | Claude Sonnet 4.5 (Thinking) | 86.03 |
| 4 | Mistral Small 3.1 | 84.87 |
| 5 | Mistral Small 3 | 82.73 |
| 6 | Gemini 3 Pro (Preview) | 81.22 |
| 7 | Claude Sonnet 4.6 | 80.69 |
| 8 | Qwen 3 Next 80B A3B Instruct | 79.82 |
| 9 | Llama 3.1 405B Instruct FP8 | 79.65 |
| 10 | Gemini 2.5 Pro | 78.72 |
| 11 | Mistral Small 3.2 | 78.39 |
| 12 | Qwen 3 Next 80B A3B (Thinking) | 78.31 |
| 13 | Gemma 4 31B (IT) | 78.23 |
| 14 | Qwen 2.5 72B Instruct | 77.63 |
| 15 | Llama 3.3 70B Instruct | 76.56 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-italian-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.