Evals for Every Language - Language cy: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Flash Lite | 82.03 |
| 2 | Claude Sonnet 4.5 | 81.38 |
| 3 | Gemini 3.1 Pro (Preview) | 81.37 |
| 4 | Claude Sonnet 4 | 81.01 |
| 5 | Claude Opus 4.7 | 79.87 |
| 6 | Claude Opus 4.8 | 79.83 |
| 7 | Grok 4.20 | 77.85 |
| 8 | GPT-5.5 | 77.61 |
| 9 | GPT-5 | 77.49 |
| 10 | Claude Sonnet 4.6 | 77.16 |
| 11 | GPT-5.1 | 77.07 |
| 12 | GPT-4o | 77.04 |
| 13 | GPT-5.3 | 76.36 |
| 14 | Claude Haiku 4.5 | 76 |
| 15 | GPT-5.2 | 75.84 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-cy · How It Works · Data refreshed daily, snapshot 2026-09-05.