EuroEval Catalan: leaderboard
Catalan-language EuroEval all-task suite spanning NLU, knowledge, common-sense reasoning, reading comprehension, summarization, and related tasks.
Metric: Average Score (%). Source: euroeval.com. Saturation forecast: Around March 2027. 219 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash (Thinking) | 68.12 | #245 (Gemini 2.5 Flash) |
| 2 | GPT-5 | 67.73 | #98 |
| 3 | Gemini 3 Pro (Preview) | 67.59 | #66 |
| 4 | Gemini 2.5 Pro | 67.42 | #152 |
| 5 | Gemini 3 Flash (Preview) (Thinking) | 66.38 | #82 (Gemini 3 Flash (Preview)) |
| 6 | Qwen 3.5 27B FP8 | 64.83 | #164 |
| 7 | Claude Sonnet 4.5 (Thinking) | 64.24 | #142 (Claude Sonnet 4.5) |
| 8 | Qwen 3.5 35B A3B FP8 | 63.61 | #362 |
| 9 | GPT-5.4 Mini (2026-03-17) (High) | 62.8 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 10 | Gemini 3 Flash (Preview) (Non-reasoning) | 62.57 | #82 (Gemini 3 Flash (Preview)) |
| 11 | Claude Sonnet 4.6 | 61.43 | #90 |
| 12 | Claude Sonnet 4.5 (Non-reasoning) | 60.97 | #142 (Claude Sonnet 4.5) |
| 13 | Qwen 3.5 35B A3B Base | 60.6 | #310 |
| 14 | Gemini 2.5 Flash (Non-reasoning) | 60.38 | #245 (Gemini 2.5 Flash) |
| 15 | Qwen 3 32B (Non-reasoning) | 59.81 | #443 (Qwen 3 32B) |
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 · How It Works · Data refreshed daily, snapshot 2026-10-20.