Evals for Every Language - Spanish (es): leaderboard
Average score across evaluation tasks in Spanish (es), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around April 2027. 67 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Flash Lite | 80.15 | #191 |
| 2 | Claude Sonnet 4 | 78.92 | #199 |
| 3 | Gemini 3.1 Pro (Preview) | 78.89 | #58 |
| 4 | Claude Sonnet 4.5 | 78.25 | #142 |
| 5 | Grok 4.20 | 77.85 | #175 |
| 6 | GPT-5.1 | 77.83 | #135 |
| 7 | GPT-5.2 | 77.63 | #110 |
| 8 | Claude Sonnet 4.6 | 77.28 | #90 |
| 9 | Gemini 2.5 Pro | 77.17 | #152 |
| 10 | GPT-5.3 | 77.15 | #103 |
| 11 | GPT-OSS-120B | 76.58 | #341 |
| 12 | GPT-5 | 76.38 | #98 |
| 13 | Claude Haiku 4.5 | 75.95 | #280 |
| 14 | Gemma 3 27B (IT) | 75.93 | #523 |
| 15 | Nova Pro (v1) | 75.91 | #497 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-es · How It Works · Data refreshed daily, snapshot 2026-10-20.