FLORES European Languages Leaderboard: leaderboard
European-language subset of FLORES-200 machine translation, focusing on translation quality across European language pairs.
Metric: Average chrF. Source: huggingface.co. Saturation forecast: Estimated already saturated. 20 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | EuroLLM-9B-Instruct | 50.86 | #1054 |
| 2 | Gemma 3 12B (IT) | 50.03 | #664 |
| 3 | Phi-4 | 45.74 | #706 |
| 4 | Qwen 3 14B | 45.64 | #537 |
| 5 | Mistral Nemo Instruct (2407) | 43.28 | #936 |
| 6 | Qwen 3 8B | 43.25 | #674 |
| 7 | cogito-v1-preview-qwen-14B | 42.79 | |
| 8 | Qwen 2.5 14B Instruct | 42.36 | #647 |
| 9 | Qwen 2.5 7B Instruct | 39.84 | #862 |
| 10 | Mistral 7B Instruct (v0.2) | 39.33 | #1333 |
| 11 | Bielik-11B-v2 | 35.73 | #1329 |
| 12 | Bielik-7B-Instruct-v0.1 | 26.45 | #1292 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=flores-european-languages-leaderboard · How It Works · Data refreshed daily, snapshot 2026-10-20.