Evals for Every Language - Language ff — leaderboard
Metric: Average Score (%). Source: huggingface.co. 67 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 89.63 |
| 2 | DeepSeek V3.1 | 83.33 |
| 3 | Claude Opus 4.8 | 82.96 |
| 4 | Claude Opus 4.7 | 79.17 |
| 5 | GPT-5.5 | 78.06 |
| 6 | Claude Sonnet 4.6 | 75.93 |
| 7 | DeepSeek V3.2 Exp | 68.25 |
| 8 | Claude Sonnet 4.5 | 66.67 |
| 9 | Grok 4.20 | 66.67 |
| 10 | GPT-5.4 | 64.81 |
| 11 | Gemini 3.1 Flash Lite | 64.29 |
| 12 | Gemini 2.5 Pro | 63.33 |
| 13 | Claude Sonnet 4 | 63.33 |
| 14 | Qwen 3.6 Plus | 63.33 |
| 15 | GLM 4.5 Air | 58.33 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-ff · How the rankings work · Data refreshed daily, snapshot 2026-07-22.