# EuroEval

Tests how well AI language models understand and write in more than 30 European languages, across many kinds of tasks. It matters because most AI tests are English-only.

Category: multilingual. Type: leaderboard. Status: active.
Metric: Average rank score across languages and tasks (lower is better; 1.00 would mean best on everything) (lower is better).
Source: EuroEval team — https://euroeval.com/leaderboards/Multilingual/european/, results as of 2026-11-15, retrieved 2026-11-17, license: not stated.

| Rank | Model | Mean rank score | Open weights |
|---|---|---|---|
| 1 | gpt-6-astra (zero-shot, val) | 1.17 ± 0.05 | No |
| 1 | gpt-6.1-sol (zero-shot, val) | 1.18 ± 0.04 | No |
| 2 | gemini/gemini-3.7-flash (zero-shot, val) | 1.24 ± 0.03 | No |
| 3 | gemini/gemini-3-flash-preview#thinking (zero-shot, val) | 1.32 ± 0.04 | No |
| 3 | gemini/gemini-3.6-flash (zero-shot, val) | 1.31 ± 0.04 | No |
| 3 | zai-org/GLM-5.3-Flash (val) | 1.36 ± 0.04 | Yes |
| 4 | gpt-5.6-sol (zero-shot, val) | 1.40 ± 0.04 | No |
| 5 | gpt-6-sol (zero-shot, val) | 1.45 ± 0.05 | No |
| 6 | zai-org/GLM-5.3-Flash (zero-shot, val) | 1.54 ± 0.08 | Yes |
| 6 | deepseek/deepseek-flash#low (zero-shot, val) | 1.50 ± 0.05 | No |
| 7 | Qwen/Qwen3.6-27B-FP8 (val) | 1.60 ± 0.07 | Yes |
| 7 | gemini/gemini-3.1-flash-lite-preview (zero-shot, val) | 1.59 ± 0.08 | No |
| 7 | gpt-5.6-terra (zero-shot, val) | 1.58 ± 0.07 | No |
| 7 | openai/gpt-5.4-mini-2026-03-17#high (zero-shot, val) | 1.61 ± 0.05 | No |
| 7 | claude-sonnet-4-5-20250929#thinking (zero-shot, val) | 1.56 ± 0.08 | No |
| 7 | deepseek/deepseek-flash#no-thinking (val) | 1.57 ± 0.06 | No |
| 8 | Qwen/Qwen3.8-27B (val) | 1.67 ± 0.09 | Yes |
| 8 | Qwen/Qwen3.5-35B-A3B-FP8 (val) | 1.66 ± 0.09 | Yes |
| 8 | google/gemma-4-31B-it (val) | 1.67 ± 0.10 | Yes |
| 8 | claude-sonnet-4-6 (zero-shot, val) | 1.69 ± 0.08 | No |
| 8 | xai/grok-4-1-fast-reasoning (zero-shot, val) | 1.69 ± 0.07 | No |
| 8 | openai/gpt-5.4-mini-2026-03-17#medium (zero-shot, val) | 1.64 ± 0.06 | No |
| 9 | gpt-5-mini-2025-08-07 (zero-shot, val) | 1.71 ± 0.07 | No |
| 9 | openai/gpt-5.4-mini-2026-03-17#low (zero-shot, val) | 1.70 ± 0.06 | No |
| 9 | openai/gpt-5.4-2026-03-05#none (zero-shot, val) | 1.76 ± 0.09 | No |

Notes: European (all languages) leaderboard, All Models view, simplified CSV embedded in the site bundle. Rank score: lower is better. Ties share ranks.
