European LLM Leaderboard - Accuracy: leaderboard
European LLM leaderboard averaging multilingual accuracy, zero-shot accuracy, and FLORES200 translation scores over 21 European languages.
Metric: Average Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 52 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.1 70B Instruct | 70.57 | #561 |
| 2 | Gemma 2 27B (IT) | 69.8 | #645 |
| 3 | Mixtral 8x7B Instruct (v0.1) | 59.11 | #1073 |
| 4 | Gemma 2 9B (IT) | 58.06 | #788 |
| 5 | EuroLLM-9B-Instruct | 57.67 | #1054 |
| 6 | Llama 3.1 8B Instruct | 56.21 | #1035 |
| 7 | Mixtral 8x7B (v0.1) | 55.4 | #1083 |
| 8 | Llama 3 8B Instruct | 54.73 | #1129 |
| 9 | Qwen 2 7B | 54.24 | #1095 |
| 10 | gemma-7B | 53.55 | #1384 |
| 11 | Qwen 2 7B Instruct | 52.79 | #991 |
| 12 | Llama 3.1 8B | 51.16 | #1151 |
| 13 | Llama 3 8B | 50.27 | #1242 |
| 14 | mistral-nemo-minitron-8B-base | 50.21 | #1087 |
| 15 | Mistral 7B Instruct (v0.3) | 48.19 | #1274 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=european-llm-leaderboard-accuracy · How It Works · Data refreshed daily, snapshot 2026-10-20.