Evals for Every Language - Occitan (oc): leaderboard
Average score across evaluation tasks in Occitan (oc), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 67 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 81.84 | #58 |
| 2 | Claude Opus 4.8 | 80.22 | #37 |
| 3 | Gemini 3.1 Flash Lite | 79.84 | #191 |
| 4 | Claude Sonnet 4.6 | 79.8 | #90 |
| 5 | GPT-4o | 79.77 | #343 |
| 6 | GPT-5.4 | 79.34 | #79 |
| 7 | Claude Opus 4.7 | 79.25 | #49 |
| 8 | Gemini 2.5 Pro | 79.18 | #152 |
| 9 | Grok 4.20 | 78.13 | #175 |
| 10 | GPT-5.2 | 77.81 | #110 |
| 11 | GPT-5.1 | 77.44 | #135 |
| 12 | Claude Sonnet 4.5 | 77.07 | #142 |
| 13 | GPT-5.5 | 76.66 | #31 |
| 14 | Claude Sonnet 4 | 76.54 | #199 |
| 15 | Qwen 3.6 Plus | 76.09 | #120 |
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-oc · How It Works · Data refreshed daily, snapshot 2026-10-20.