List your company

Commonsense Reasoning on Hellaswag Multilingual (test)

83.1AccuracyMistral-3.2-24B
27.9842.2956.670.91Feb 5, 2026

Evaluation results

MethodLinks
Mistral-3.2-24BOpenness=Open-weights, Region=European, Tuning=Instruction-tuned2026.0283.1
Qwen-3-32BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.0279.6
Qwen-3-30B-A3BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.0278.5
Qwen-3-14BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.0276.4
Gemma-3-27BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.0275.6
Gemma-3-12BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.0273.5
Llama-3.3-70BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.0273.4
Apertus-70BOpenness=Fully-open, Region=European, Tuning=Instruction-tuned2026.0267.4
EuroLLM-22B (old)Openness=Fully-open, Region=European, Tuning=Instruction-tuned2026.0265
EuroLLM-22B (new)Openness=Fully-open, Region=European, Tuning=Instruction-tuned2026.0262.3
EuroLLM-9B (old)Openness=Fully-open, Region=European, Tuning=Instruction-tuned2026.0253.9
Apertus-8BOpenness=Fully-open, Region=European, Tuning=Instruction-tuned2026.0250.2
EuroLLM-9B (new)Openness=Fully-open, Region=European, Tuning=Instruction-tuned2026.0249.1
OLMo-3.1-32BOpenness=Fully-open, Region=Non-European, Tuning=Instruction-tuned2026.0247.4
Llama-3.1-8BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.0237.4
OLMo-3-7BOpenness=Fully-open, Region=Non-European, Tuning=Instruction-tuned2026.0230.1