Evals for Every Language - Language lt: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 74.4 |
| 2 | Claude Sonnet 4.5 | 73.1 |
| 3 | Claude Opus 4.8 | 71.32 |
| 4 | GPT-5.2 | 70.94 |
| 5 | Claude Opus 4.7 | 70.44 |
| 6 | GPT-5.3 | 70.13 |
| 7 | GPT-5.5 | 69.49 |
| 8 | Claude Sonnet 4 | 69.34 |
| 9 | Claude Sonnet 4.6 | 68.83 |
| 10 | Gemini 3.1 Flash Lite | 68.71 |
| 11 | GPT-5 | 68.28 |
| 12 | Grok 4.20 | 67.98 |
| 13 | Qwen 3.6 Plus | 67.92 |
| 14 | GPT-5.4 | 67.89 |
| 15 | GLM 4.5 Air | 67.87 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-lt · How It Works · Data refreshed daily, snapshot 2026-09-05.