Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multitask Language Understanding on TMLU
Loading...
37.17
Accuracy
Dense
23.8476
27.3063
30.765
34.2237
Jun 15, 2025
Accuracy
Updated 20d ago
Evaluation Results
Method
Method
Links
Accuracy
Dense
Base Model=DeepSeek-7B...
2025.06
37.17
Dense
Base Model=LLaMA-2-7B,...
2025.06
29.58
Sparsegpt
Base Model=DeepSeek-7B...
2025.06
25.99
MaskPro
Base Model=LLaMA-2-7B,...
2025.06
25.38
MaskPro
Base Model=DeepSeek-7B...
2025.06
25.37
Pruner-Z
Base Model=LLaMA-2-7B,...
2025.06
25.13
Sparsegpt
Base Model=LLaMA-2-7B,...
2025.06
25.03
Pruner-Z
Base Model=DeepSeek-7B...
2025.06
24.36
Feedback
Search any
task
Search any
task
