Evals for Every Language - Xhosa (xh): leaderboard
Average score across evaluation tasks in Xhosa (xh), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 65 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 74.37 | #58 |
| 2 | Claude Sonnet 4.6 | 73.31 | #90 |
| 3 | Grok 4.20 | 70.93 | #175 |
| 4 | GPT-5 | 70.8 | #98 |
| 5 | Claude Opus 4.7 | 70.47 | #49 |
| 6 | GPT-5.1 | 70.37 | #135 |
| 7 | Claude Sonnet 4 | 70.02 | #199 |
| 8 | GPT-5.5 | 70.02 | #31 |
| 9 | Claude Sonnet 4.5 | 70 | #142 |
| 10 | Claude Opus 4.8 | 69.99 | #37 |
| 11 | GPT-5.3 | 69.82 | #103 |
| 12 | GPT-5.2 | 68.65 | #110 |
| 13 | GPT-5.4 | 68.06 | #79 |
| 14 | GPT-4o | 65.61 | #343 |
| 15 | Gemini 3.1 Flash Lite | 64.65 | #191 |
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-xh · How It Works · Data refreshed daily, snapshot 2026-10-20.