Evals for Every Language - Language yo: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 67.1 |
| 2 | Gemini 3.1 Flash Lite | 63.58 |
| 3 | Claude Opus 4.7 | 60.79 |
| 4 | Claude Opus 4.8 | 60.79 |
| 5 | GPT-5.3 | 59.22 |
| 6 | GPT-5.5 | 59.01 |
| 7 | GPT-5.2 | 58.1 |
| 8 | Qwen 3.6 Plus | 57.59 |
| 9 | Grok 4.20 | 57.51 |
| 10 | GPT-5.4 | 57.38 |
| 11 | Claude Sonnet 4.6 | 57.02 |
| 12 | DeepSeek V3.1 | 56.04 |
| 13 | Claude Sonnet 4.5 | 53.82 |
| 14 | GPT-5 | 52.26 |
| 15 | GPT-5.1 | 49.96 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-yo · How It Works · Data refreshed daily, snapshot 2026-09-05.