Evals for Every Language - Language gl: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 73.21 |
| 2 | Claude Opus 4.8 | 72.87 |
| 3 | GPT-5 | 72.31 |
| 4 | Gemini 2.5 Pro | 71.5 |
| 5 | Claude Sonnet 4.6 | 71.13 |
| 6 | Claude Sonnet 4 | 70.87 |
| 7 | Claude Sonnet 4.5 | 70.76 |
| 8 | GPT-4o | 70.66 |
| 9 | Gemini 3.1 Flash Lite | 70.25 |
| 10 | GPT-5.2 | 70.17 |
| 11 | GPT-5.3 | 69.95 |
| 12 | GPT-5.1 | 69.62 |
| 13 | Grok 4.20 | 69.6 |
| 14 | GPT-5.5 | 69.31 |
| 15 | Claude Opus 4.7 | 69.02 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-gl · How It Works · Data refreshed daily, snapshot 2026-09-05.