EuroEval Catalan Common Sense Reasoning: leaderboard
EuroEval's Catalan common-sense reasoning task — multiple-choice questions testing everyday physical and social reasoning in Catalan, from the EuroEval European language model benchmark suite.
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. Saturation forecast: Around May 2027. 194 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) (Thinking) | 80.44 | #82 (Gemini 3 Flash (Preview)) |
| 2 | Qwen 3.5 27B FP8 | 80.3 | #164 |
| 3 | Claude Sonnet 4.5 (Thinking) | 77.83 | #142 (Claude Sonnet 4.5) |
| 4 | Gemini 3 Pro (Preview) | 77.76 | #66 |
| 5 | GPT-5 | 77.01 | #98 |
| 6 | Qwen 3.5 35B A3B FP8 | 71.9 | #362 |
| 7 | Gemini 2.5 Flash (Thinking) | 70.94 | #245 (Gemini 2.5 Flash) |
| 8 | Grok 4.20 Beta (0309) (Reasoning) | 70.28 | #204 (Grok 4.20 Beta (0309)) |
| 9 | Gemini 2.5 Pro | 66.44 | #152 |
| 10 | Claude Sonnet 4.5 (Non-reasoning) | 65.98 | #142 (Claude Sonnet 4.5) |
| 11 | Gemini 3 Flash (Preview) (Non-reasoning) | 63.04 | #82 (Gemini 3 Flash (Preview)) |
| 12 | GPT-5 Mini (2025-08-07) | 61.19 | #172 |
| 13 | Qwen 3.5 35B A3B Base | 60.13 | #310 |
| 14 | Gemma 4 31B (IT) | 60.12 | #176 |
| 15 | GPT-5.4 Mini (2026-03-17) (High) | 58.95 | #169 (GPT-5.4 Mini (2026-03-17)) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-catalan-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.