List your company
ResearchFormerly WizWand

Multilingual Language Understanding on MMMLU (Massive Multilingual Language Understanding)

79.5AccuracyQwen-3-30B-A3B
30.266443.048255.8368.6118Nov 28, 2025Dec 9, 2025Dec 21, 2025Jan 1, 2026Jan 13, 2026Jan 24, 2026Feb 5, 2026
Updated 8mo ago

Evaluation results

MethodLinks
Qwen-3-30B-A3BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.0279.5
Qwen-3-32BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.0279
Llama-3.3-70BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.0278.4
Mistral-3.2-24BOpenness=Open-weights, Region=European, Tuning=Instruction-tuned2026.0274.8
Qwen-3-14BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.0274.7
Gemma-3-27BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.0274.6
Gemma-3-12BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.0269
OLMo-3.1-32BOpenness=Fully-open, Region=Non-European, Tuning=Instruction-tuned2026.0266.5
EuroLLM-22B (new)Openness=Fully-open, Region=European, Tuning=Instruction-tuned2026.0264.1
Apertus-70BOpenness=Fully-open, Region=European, Tuning=Instruction-tuned2026.0260.3
EuroLLM-9B (new)Openness=Fully-open, Region=European, Tuning=Instruction-tuned2026.0260.2
EuroLLM-22B (old)Openness=Fully-open, Region=European, Tuning=Instruction-tuned2026.0259.7
Qwen2.5-VL-3B# Total Params=3.75B, Evaluation Toolkit=internal language eval suite2025.1154.23
EuroLLM-9B (old)Openness=Fully-open, Region=European, Tuning=Instruction-tuned2026.0253.8
LFM2-VL-3B# Total Params=3.0B, Evaluation Toolkit=internal language eval suite2025.1153.37
Apertus-8BOpenness=Fully-open, Region=European, Tuning=Instruction-tuned2026.0253
Llama-3.1-8BOpenness=Open-weights, Region=Non-European, Tuning=Instruction-tuned2026.0252.9
InternVL3.5-2B# Total Params=2.3B, Evaluation Toolkit=internal language eval suite2025.1149.32
OLMo-3-7BOpenness=Fully-open, Region=Non-European, Tuning=Instruction-tuned2026.0248.3
Qwen3-VL-2B# Total Params=2.1B, Evaluation Toolkit=internal language eval suite2025.1142.2
SmolVLM2-2.2B# Total Params=2.2B, Evaluation Toolkit=internal language eval suite2025.1132.16