Evals for Every Language - Language luo: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 64.57 |
| 2 | Claude Opus 4.7 | 63.26 |
| 3 | Claude Opus 4.8 | 62.69 |
| 4 | Gemini 3.1 Flash Lite | 59.6 |
| 5 | Gemini 2.5 Pro | 58.94 |
| 6 | Grok 4.20 | 55.7 |
| 7 | GPT-5.5 | 54.37 |
| 8 | Claude Sonnet 4.5 | 50.45 |
| 9 | GPT-5.4 | 50.05 |
| 10 | GPT-5.3 | 49 |
| 11 | Claude Sonnet 4.6 | 47.72 |
| 12 | GPT-5 | 47.49 |
| 13 | Claude Sonnet 4 | 46.24 |
| 14 | GPT-5.2 | 45.51 |
| 15 | GPT-4o | 44.27 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-luo · How It Works · Data refreshed daily, snapshot 2026-09-05.