EuroEval Catalan Common Sense Reasoning: leaderboard
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. 194 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 77.83 |
| 2 | Gemini 3 Pro (Preview) | 77.76 |
| 3 | GPT-5 | 77.01 |
| 4 | Gemini 2.5 Flash (Thinking) | 70.94 |
| 5 | Grok 4.20 Beta (0309) (Reasoning) | 70.28 |
| 6 | Gemini 2.5 Pro | 66.44 |
| 7 | Claude Sonnet 4.5 (Non-reasoning) | 65.98 |
| 8 | GPT-5 Mini | 61.19 |
| 9 | Gemma 4 31B (IT) | 60.12 |
| 10 | GPT-5.4 Mini (High) | 58.95 |
| 11 | GPT-5.4 Mini (Medium) | 58.52 |
| 12 | Qwen 3.5 9B | 56.89 |
| 13 | Grok 4.1 Fast (Reasoning) | 56.57 |
| 14 | Qwen 3.5 4B | 55.1 |
| 15 | Llama 3.3 70B Instruct | 54.47 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-catalan-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.