Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Massive Multitask Language Understanding on MMLU (5-shot)
Loading...
59.69
MMLU (5-shot)
FP16
23.5916
32.9633
42.335
51.7067
Jun 5, 2025
MMLU (5-shot)
Updated 17d ago
Evaluation Results
Method
Method
Links
MMLU (5-shot)
FP16
Model=Llama-3.2 3B-it,...
2025.06
59.69
FlatQuant
Model=Llama-3.2 3B-it,...
2025.06
55.46
FPTQuant
Model=Llama-3.2 3B-it,...
2025.06
52.62
SpinQuant
Model=Llama-3.2 3B-it,...
2025.06
52.14
QuaRot
Model=Llama-3.2 3B-it,...
2025.06
51.68
FlatQuant
Model=Llama-3.2 3B-it,...
2025.06
49.01
RTN-opt
Model=Llama-3.2 3B-it,...
2025.06
46.45
FPTQuant
Model=Llama-3.2 3B-it,...
2025.06
43.71
SpinQuant
Model=Llama-3.2 3B-it,...
2025.06
38.17
QuaRot
Model=Llama-3.2 3B-it,...
2025.06
35.72
RTN-opt
Model=Llama-3.2 3B-it,...
2025.06
24.98
Feedback
Search any
task
Search any
task
