Evals for Every Language - Nuer (nus): leaderboard
Average score across evaluation tasks in Nuer (nus), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around February 2028. 62 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 60.45 | #37 |
| 2 | Claude Opus 4.7 | 60.24 | #49 |
| 3 | Claude Sonnet 4.6 | 58.13 | #90 |
| 4 | GPT-5.5 | 56.91 | #31 |
| 5 | Gemini 3.1 Pro (Preview) | 54.09 | #58 |
| 6 | Gemini 3.1 Flash Lite | 41.18 | #191 |
| 7 | GPT-5.4 | 38.33 | #79 |
| 8 | Gemini 2.5 Pro | 36.58 | #152 |
| 9 | Ministral 3 8B | 35.22 | #687 |
| 10 | GPT-5.1 | 34.69 | #135 |
| 11 | Claude Sonnet 4 | 34.26 | #199 |
| 12 | Claude Sonnet 4.5 | 34.09 | #142 |
| 13 | GPT-5.2 | 34 | #110 |
| 14 | Mistral Medium 3.1 | 32.48 | #408 |
| 15 | GLM 4.5 Air | 32.41 | #392 |
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-nus · How It Works · Data refreshed daily, snapshot 2026-10-20.