Commonsense Reasoning on Hellaswag non-EU languages (test)
80.4AccuracyMistral-3.2-24B
Evaluation Results
| Method | Links | |
|---|---|---|
| Mistral-3.2-24BRelease Type=Open-weights, Model Category=European2026.02 | 80.4 | |
| Qwen-3-32BRelease Type=Open-weights, Model Category=Non-European2026.02 | 77.4 | |
| Qwen-3-30B-A3BRelease Type=Open-weights, Model Category=Non-European2026.02 | 76.6 | |
| Qwen-3-14BRelease Type=Open-weights, Model Category=Non-European2026.02 | 73.8 | |
| Gemma-3-27BRelease Type=Open-weights, Model Category=Non-European2026.02 | 73.6 | |
| Gemma-3-12BRelease Type=Open-weights, Model Category=Non-European2026.02 | 71.1 | |
| Llama-3.3-70BRelease Type=Open-weights, Model Category=Non-European2026.02 | 70.2 | |
| Apertus-70BRelease Type=Fully-open, Model Category=European2026.02 | 64.5 | |
| EuroLLM-22B (new)Release Type=Fully-open, Model Category=European2026.02 | 61.7 | |
| EuroLLM-22B (old)Release Type=Fully-open, Model Category=European2026.02 | 61.4 | |
| EuroLLM-9B (old)Release Type=Fully-open, Model Category=European2026.02 | 50.1 | |
| Apertus-8BRelease Type=Fully-open, Model Category=European2026.02 | 48.7 | |
| EuroLLM-9B (new)Release Type=Fully-open, Model Category=European2026.02 | 47.3 | |
| OLMo-3.1-32BRelease Type=Fully-open, Model Category=Non-European2026.02 | 43.3 | |
| Llama-3.1-8BRelease Type=Open-weights, Model Category=Non-European2026.02 | 36.6 | |
| OLMo-3-7BRelease Type=Fully-open, Model Category=Non-European2026.02 | 30.3 |