EuroEval Spanish: leaderboard
Spanish-language EuroEval all-task suite spanning NLU, knowledge, common-sense reasoning, reading comprehension, summarization, and related tasks.
Metric: Average Score (%). Source: euroeval.com. Saturation forecast: Around March 2027. 419 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 68.78 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 2 | Qwen 3 235B A22B 2507 Instruct | 66.09 | #300 |
| 3 | Gemini 3 Pro (Preview) | 65.83 | #66 |
| 4 | GPT-5 (2025-08-07) (High) | 65.42 | |
| 5 | Claude Sonnet 4.6 | 65.09 | #90 |
| 6 | Qwen 3 Next 80B A3B Instruct | 64.72 | #368 |
| 7 | O3 (2025-04-16) | 64.31 | #121 |
| 8 | Gemini 3 Flash (Preview) (Non-reasoning) | 64.12 | #82 (Gemini 3 Flash (Preview)) |
| 9 | Llama 3.1 405B Instruct FP8 | 64.11 | #389 |
| 10 | GPT-5.4 Mini (2026-03-17) (High) | 63.94 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 11 | GPT-5 | 63.37 | #98 |
| 12 | Qwen 3 235B A22B | 63.33 | #313 |
| 13 | Gemini 3 Flash (Preview) (Thinking) | 62.86 | #82 (Gemini 3 Flash (Preview)) |
| 14 | Gemini 2.5 Pro | 62.44 | #152 |
| 15 | Llama 3.1 405B | 62.44 | #466 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-spanish · How It Works · Data refreshed daily, snapshot 2026-10-20.