Evals for Every Language - Catalan (ca): leaderboard
Average score across evaluation tasks in Catalan (ca), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 66 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Flash Lite | 80.38 | #191 |
| 2 | Gemini 3.1 Pro (Preview) | 78.49 | #58 |
| 3 | Claude Opus 4.8 | 78.25 | #37 |
| 4 | Gemini 2.5 Pro | 77.97 | #152 |
| 5 | Claude Sonnet 4 | 77.6 | #199 |
| 6 | GPT-5.5 | 77.29 | #31 |
| 7 | Claude Haiku 4.5 | 77.18 | #280 |
| 8 | DeepSeek V3.2 Exp | 76.94 | #234 |
| 9 | GPT-4o | 76.82 | #343 |
| 10 | GPT-5.3 | 76.79 | #103 |
| 11 | GPT-5 | 76.71 | #98 |
| 12 | GPT-5.1 | 76.61 | #135 |
| 13 | GPT-5.2 | 76.47 | #110 |
| 14 | Claude Sonnet 4.5 | 76.34 | #142 |
| 15 | DeepSeek V3.1 | 76.33 | #264 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-ca · How It Works · Data refreshed daily, snapshot 2026-10-20.