Commonsense Reasoning on Hellaswag Multilingual (test)
83.1AccuracyMistral-3.2-24B
Evaluation Results
| Method | Links | |
|---|---|---|
| Mistral-3.2-24BOpenness=Open-weights, Region=European, Tuning=Instruction-tuned2026.02 | 83.1 | |
| Qwen-3-32BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.02 | 79.6 | |
| Qwen-3-30B-A3BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.02 | 78.5 | |
| Qwen-3-14BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.02 | 76.4 | |
| Gemma-3-27BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.02 | 75.6 | |
| Gemma-3-12BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.02 | 73.5 | |
| Llama-3.3-70BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.02 | 73.4 | |
| Apertus-70BOpenness=Fully-open, Region=European, Tuning=Instruction-tuned2026.02 | 67.4 | |
| EuroLLM-22B (old)Openness=Fully-open, Region=European, Tuning=Instruction-tuned2026.02 | 65 | |
| EuroLLM-22B (new)Openness=Fully-open, Region=European, Tuning=Instruction-tuned2026.02 | 62.3 | |
| EuroLLM-9B (old)Openness=Fully-open, Region=European, Tuning=Instruction-tuned2026.02 | 53.9 | |
| Apertus-8BOpenness=Fully-open, Region=European, Tuning=Instruction-tuned2026.02 | 50.2 | |
| EuroLLM-9B (new)Openness=Fully-open, Region=European, Tuning=Instruction-tuned2026.02 | 49.1 | |
| OLMo-3.1-32BOpenness=Fully-open, Region=Non-European, Tuning=Instruction-tuned2026.02 | 47.4 | |
| Llama-3.1-8BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.02 | 37.4 | |
| OLMo-3-7BOpenness=Fully-open, Region=Non-European, Tuning=Instruction-tuned2026.02 | 30.1 |