EuroEval French Common Sense Reasoning: leaderboard
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. 343 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Non-reasoning) | 87.88 |
| 2 | Claude Sonnet 4.5 (Thinking) | 86.69 |
| 3 | Qwen 3 235B A22B 2507 Instruct | 85.74 |
| 4 | Claude Sonnet 4.6 | 83.7 |
| 5 | Mistral Small 3 | 83.43 |
| 6 | Mistral Small 3.1 | 83.4 |
| 7 | Gemini 3 Pro (Preview) | 81.83 |
| 8 | Qwen 3 Next 80B A3B Instruct | 80.37 |
| 9 | Llama 3.1 405B Instruct FP8 | 80.01 |
| 10 | Gemini 2.5 Pro | 79.86 |
| 11 | Gemma 4 31B (IT) | 78.7 |
| 12 | Mistral Small 3.2 | 78.51 |
| 13 | Qwen 2.5 72B Instruct | 77.8 |
| 14 | Qwen 3 Next 80B A3B (Thinking) | 77.39 |
| 15 | GPT-5 (High) | 76.43 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-french-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.