Mathematical Reasoning on MGSM 24 official EU languages
93AccuracyLlama-3.3-70B
Evaluation Results
| Method | Links | |
|---|---|---|
| Llama-3.3-70BWeights accessibility=Open-weights, Regional origin=Non-European2026.02 | 93 | |
| Qwen-3-32BWeights accessibility=Open-weights, Regional origin=Non-European2026.02 | 92 | |
| Qwen-3-30B-A3BWeights accessibility=Open-weights, Regional origin=Non-European2026.02 | 91.4 | |
| Mistral-3.2-24BWeights accessibility=Open-weights, Regional origin=European2026.02 | 90.8 | |
| Qwen-3-14BWeights accessibility=Open-weights, Regional origin=Non-European2026.02 | 90.3 | |
| Gemma-3-27BWeights accessibility=Open-weights, Regional origin=Non-European2026.02 | 89.9 | |
| OLMo-3.1-32BWeights accessibility=Fully-open, Regional origin=Non-European2026.02 | 88.8 | |
| Gemma-3-12BWeights accessibility=Open-weights, Regional origin=Non-European2026.02 | 87.5 | |
| OLMo-3-7BWeights accessibility=Fully-open, Regional origin=Non-European2026.02 | 80.6 | |
| EuroLLM-22BWeights accessibility=Fully-open, Regional origin=European2026.02 | 77.8 | |
| Llama-3.1-8BWeights accessibility=Open-weights, Regional origin=Non-European2026.02 | 75.6 | |
| Apertus-70BWeights accessibility=Fully-open, Regional origin=European2026.02 | 73.6 | |
| EuroLLM-9BWeights accessibility=Fully-open, Regional origin=European2026.02 | 71 | |
| Apertus-8BWeights accessibility=Fully-open, Regional origin=European2026.02 | 61.4 |