Evals for Every Language - Language mak — leaderboard
Metric: Average Score (%). Source: huggingface.co. 68 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3.1 | 100 |
| 2 | Claude Opus 4.7 | 96.67 |
| 3 | Claude Opus 4.8 | 96.3 |
| 4 | Gemini 3.1 Pro (Preview) | 95.83 |
| 5 | GPT-5.5 | 93.33 |
| 6 | Claude Sonnet 4.6 | 91.67 |
| 7 | Gemini 2.5 Pro | 86.67 |
| 8 | GPT-5.4 | 83.33 |
| 9 | Qwen 3.6 Plus | 82.96 |
| 10 | GPT-5.1 | 81.48 |
| 11 | GPT-5.2 | 80 |
| 12 | GPT-5 | 78.15 |
| 13 | Grok 4.20 | 76.67 |
| 14 | Gemini 3.1 Flash Lite | 73.33 |
| 15 | jamba-large-1.7 | 73.02 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-mak · How the rankings work · Data refreshed daily, snapshot 2026-07-22.