Evals for Every Language - Language xh: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 68.89 |
| 2 | Claude Sonnet 4.6 | 67.27 |
| 3 | Claude Opus 4.7 | 65.79 |
| 4 | GPT-5.5 | 65.46 |
| 5 | GPT-5 | 65.43 |
| 6 | Claude Opus 4.8 | 65.37 |
| 7 | Grok 4.20 | 65.29 |
| 8 | GPT-5.1 | 64.91 |
| 9 | Claude Sonnet 4.5 | 64.87 |
| 10 | GPT-5.3 | 64.85 |
| 11 | Claude Sonnet 4 | 64.53 |
| 12 | GPT-5.4 | 63.81 |
| 13 | GPT-5.2 | 63.15 |
| 14 | GPT-4o | 61.17 |
| 15 | Gemini 2.5 Pro | 61.09 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-xh · How It Works · Data refreshed daily, snapshot 2026-09-05.