Evals for Every Language - Nyanja (ny): leaderboard
Average score across evaluation tasks in Nyanja (ny), 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) | 73.83 | #58 |
| 2 | Claude Opus 4.8 | 71.68 | #37 |
| 3 | Claude Opus 4.7 | 70.7 | #49 |
| 4 | GPT-5.1 | 70.55 | #135 |
| 5 | GPT-5.3 | 70.49 | #103 |
| 6 | Grok 4.20 | 67.98 | #175 |
| 7 | GPT-5 | 67.84 | #98 |
| 8 | Claude Sonnet 4.6 | 67.64 | #90 |
| 9 | GPT-5.5 | 67.51 | #31 |
| 10 | Gemini 3.1 Flash Lite | 67.41 | #191 |
| 11 | Gemini 2.5 Pro | 66.8 | #152 |
| 12 | GPT-5.2 | 66.79 | #110 |
| 13 | GPT-5.4 | 66.64 | #79 |
| 14 | Claude Sonnet 4.5 | 66.54 | #142 |
| 15 | Gemini 2.5 Flash Lite | 64.04 | #422 |
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-ny · How It Works · Data refreshed daily, snapshot 2026-10-20.