Evals for Every Language - Language lmo: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 67.8 |
| 2 | Claude Opus 4.7 | 66.39 |
| 3 | Gemini 3.1 Flash Lite | 66.11 |
| 4 | Gemini 2.5 Pro | 65.68 |
| 5 | Claude Sonnet 4 | 65.41 |
| 6 | Claude Sonnet 4.6 | 65.16 |
| 7 | Grok 4.20 | 65.06 |
| 8 | GPT-5 | 65.01 |
| 9 | GPT-5.3 | 64.95 |
| 10 | GPT-5.4 | 64.8 |
| 11 | Claude Sonnet 4.5 | 64.41 |
| 12 | Claude Opus 4.8 | 64.41 |
| 13 | GPT-5.2 | 64.02 |
| 14 | GPT-5.1 | 63.62 |
| 15 | GPT-5.5 | 63.48 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-lmo · How It Works · Data refreshed daily, snapshot 2026-09-05.