Evals for Every Language - Language ltg — leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 71.23 |
| 2 | Claude Opus 4.7 | 68.83 |
| 3 | Gemini 2.5 Pro | 67.85 |
| 4 | Gemini 3.1 Flash Lite | 66.86 |
| 5 | Claude Sonnet 4.5 | 66.83 |
| 6 | GPT-5.1 | 65.87 |
| 7 | Claude Opus 4.8 | 65.69 |
| 8 | GPT-5.5 | 65.41 |
| 9 | GPT-5 | 64.24 |
| 10 | Qwen 3.6 Plus | 63.65 |
| 11 | Grok 4.20 | 63.44 |
| 12 | GPT-5.2 | 62.45 |
| 13 | DeepSeek V3.1 | 62.42 |
| 14 | Claude Sonnet 4.6 | 62.33 |
| 15 | Claude Sonnet 4 | 61.85 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-ltg · How the rankings work · Data refreshed daily, snapshot 2026-07-22.