EuroEval Spanish: leaderboard
Metric: Average Score (%). Source: euroeval.com. 419 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 235B A22B 2507 Instruct | 66.09 |
| 2 | Gemini 3 Pro (Preview) | 65.83 |
| 3 | GPT-5 (High) | 65.42 |
| 4 | Claude Sonnet 4.6 | 65.09 |
| 5 | Qwen 3 Next 80B A3B Instruct | 64.72 |
| 6 | O3 (2025-04-16) | 64.31 |
| 7 | Llama 3.1 405B Instruct FP8 | 64.11 |
| 8 | GPT-5.4 Mini (High) | 63.94 |
| 9 | GPT-5 | 63.37 |
| 10 | Qwen 3 235B A22B | 63.33 |
| 11 | Gemini 2.5 Pro | 62.44 |
| 12 | Llama 3.1 405B | 62.44 |
| 13 | Qwen 3 Next 80B A3B (Thinking) | 62.38 |
| 14 | Claude 3.7 Sonnet (20250219) (Thinking) | 62.26 |
| 15 | GPT-5.4 Mini (Medium) | 62.23 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-spanish · How It Works · Data refreshed daily, snapshot 2026-09-05.