Evals for Every Language - Language ps — leaderboard
Metric: Average Score (%). Source: huggingface.co. 69 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Flash Lite | 100 |
| 2 | Gemini 3.1 Pro (Preview) | 96.67 |
| 3 | GPT-5 | 96.67 |
| 4 | GPT-5.5 | 96.67 |
| 5 | Claude Opus 4.7 | 96.67 |
| 6 | GPT-5.4 | 96.67 |
| 7 | Qwen 3.6 Plus | 96.67 |
| 8 | Claude Opus 4.8 | 96.67 |
| 9 | GPT-5.1 | 96.67 |
| 10 | Grok 4.20 | 96.67 |
| 11 | Claude Sonnet 4.6 | 96.3 |
| 12 | DeepSeek V3.1 | 95.24 |
| 13 | DeepSeek V3.2 Exp | 95.24 |
| 14 | Gemma 3 27B (IT) | 93.33 |
| 15 | GPT-5.2 | 93.33 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-ps · How the rankings work · Data refreshed daily, snapshot 2026-07-22.