EuroEval Spanish Common Sense Reasoning: leaderboard
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. 379 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Non-reasoning) | 94.95 |
| 2 | Claude Sonnet 4.5 (Thinking) | 93.43 |
| 3 | Claude Sonnet 4.6 | 88.25 |
| 4 | Qwen 3 235B A22B 2507 Instruct | 86.78 |
| 5 | Gemini 3 Pro (Preview) | 86.7 |
| 6 | Mistral Small 3.1 | 84.76 |
| 7 | Gemma 4 31B (IT) | 82.78 |
| 8 | GPT-5 (Minimal) | 82.16 |
| 9 | Gemini 2.5 Pro | 81.95 |
| 10 | Mistral Small 3 | 81.7 |
| 11 | Qwen 3 Next 80B A3B Instruct | 81.12 |
| 12 | Llama 3.1 405B Instruct FP8 | 81.08 |
| 13 | Mistral Small 3.2 | 79.97 |
| 14 | Llama 3.3 70B Instruct | 79.32 |
| 15 | Claude Haiku 4.5 (20251001) | 79.3 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-spanish-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.