EuroEval Catalan: leaderboard
Metric: Average Score (%). Source: euroeval.com. 219 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash (Thinking) | 68.12 |
| 2 | GPT-5 | 67.73 |
| 3 | Gemini 3 Pro (Preview) | 67.59 |
| 4 | Gemini 2.5 Pro | 67.42 |
| 5 | Claude Sonnet 4.5 (Thinking) | 64.24 |
| 6 | GPT-5.4 Mini (High) | 62.8 |
| 7 | GPT-5.4 Mini (Medium) | 61.61 |
| 8 | Claude Sonnet 4.6 | 61.43 |
| 9 | Claude Sonnet 4.5 (Non-reasoning) | 60.97 |
| 10 | GPT-4.1 | 59.64 |
| 11 | Gemini 3.1 Flash Lite (Preview) | 59.62 |
| 12 | GPT-5 Mini | 59.56 |
| 13 | Grok 4.1 Fast (Reasoning) | 59.21 |
| 14 | GPT-5.2 | 58.32 |
| 15 | GPT-4.1 Mini | 57.52 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-catalan · How It Works · Data refreshed daily, snapshot 2026-09-05.