Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Commonsense Knowledge on MMLU-Pro
Loading...
48.4
Accuracy
Youtu-LLM
28.64
33.77
38.9
44.03
Dec 31, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Youtu-LLM
Size=2B, Type=Base, Pr...
2025.12
48.4
Qwen3
Size=4B, Type=Base, Pr...
2025.12
46.1
Llama3.1
Size=8B, Type=Base, Pr...
2025.12
36.2
SmolLM3
Size=3B, Type=Base, Pr...
2025.12
35.3
Qwen3
Size=1.7B, Type=Base,...
2025.12
34.9
Gemma3
Size=4B, Type=Base, Pr...
2025.12
29.4
Feedback
Search any
task
Search any
task
