European LLM Leaderboard - Zero-Shot Accuracy: leaderboard
European LLM leaderboard zero-shot accuracy averaged over ARC, GSM8K, HellaSwag, MMLU, and TruthfulQA across 21 European languages.
Metric: Average Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 42 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Mixtral 8x7B Instruct (v0.1) | 58.29 | #1073 |
| 2 | gemma-7B | 56.69 | #1384 |
| 3 | Mixtral 8x7B (v0.1) | 56.24 | #1083 |
| 4 | salamandra-7B-instruct | 54.36 | #1411 |
| 5 | Llama 3.1 8B Instruct | 53.12 | #1035 |
| 6 | Gemma 2 27B (IT) | 52.49 | #645 |
| 7 | Llama 3.1 8B | 52.28 | #1151 |
| 8 | Qwen 2 7B Instruct | 50.71 | #991 |
| 9 | Llama 3 8B | 50.64 | #1242 |
| 10 | Llama 3 8B Instruct | 49.76 | #1129 |
| 11 | salamandra-7B | 49.41 | #1461 |
| 12 | Mistral 7B Instruct (v0.3) | 49.06 | #1274 |
| 13 | Teuken-7B-Instruct-v0.4 | 48.22 | #1430 |
| 14 | Mistral 7B Instruct (v0.2) | 48.11 | #1333 |
| 15 | Mistral-7B-v0.1 | 46.85 | #1326 |
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-zero-shot-accuracy · How It Works · Data refreshed daily, snapshot 2026-10-20.