Mathematical Reasoning on MGSM non-EU languages (test)
91.4AccuracyQwen-3-32B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen-3-32BRelease Type=Open-weights, Model Category=Non-European2026.02 | 91.4 | |
| Llama-3.3-70BRelease Type=Open-weights, Model Category=Non-European2026.02 | 90.3 | |
| Qwen-3-14BRelease Type=Open-weights, Model Category=Non-European2026.02 | 89.8 | |
| Qwen-3-30B-A3BRelease Type=Open-weights, Model Category=Non-European2026.02 | 89.7 | |
| Mistral-3.2-24BRelease Type=Open-weights, Model Category=European2026.02 | 88.4 | |
| Gemma-3-27BRelease Type=Open-weights, Model Category=Non-European2026.02 | 87 | |
| OLMo-3.1-32BRelease Type=Fully-open, Model Category=Non-European2026.02 | 86 | |
| Gemma-3-12BRelease Type=Open-weights, Model Category=Non-European2026.02 | 84.6 | |
| EuroLLM-22B (new)Release Type=Fully-open, Model Category=European2026.02 | 74.4 | |
| OLMo-3-7BRelease Type=Fully-open, Model Category=Non-European2026.02 | 72.7 | |
| Apertus-70BRelease Type=Fully-open, Model Category=European2026.02 | 71.9 | |
| Llama-3.1-8BRelease Type=Open-weights, Model Category=Non-European2026.02 | 70.4 | |
| EuroLLM-22B (old)Release Type=Fully-open, Model Category=European2026.02 | 69.9 | |
| EuroLLM-9B (new)Release Type=Fully-open, Model Category=European2026.02 | 63.6 | |
| EuroLLM-9B (old)Release Type=Fully-open, Model Category=European2026.02 | 59.2 | |
| Apertus-8BRelease Type=Fully-open, Model Category=European2026.02 | 56.4 |