Evals for Every Language - Language es: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Flash Lite | 76.16 |
| 2 | Claude Sonnet 4.5 | 74.17 |
| 3 | Gemini 3.1 Pro (Preview) | 74.11 |
| 4 | Claude Sonnet 4 | 74.11 |
| 5 | GPT-5.1 | 73.21 |
| 6 | GPT-5.2 | 73 |
| 7 | Gemini 2.5 Pro | 72.89 |
| 8 | Grok 4.20 | 72.75 |
| 9 | Claude Sonnet 4.6 | 72.41 |
| 10 | GPT-5.3 | 72.3 |
| 11 | Gemma 3 27B (IT) | 72.28 |
| 12 | GPT-5 | 72.1 |
| 13 | Nova Pro (v1) | 71.39 |
| 14 | Claude Haiku 4.5 | 71.14 |
| 15 | GPT-5 Mini | 71.04 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-es · How It Works · Data refreshed daily, snapshot 2026-09-05.