Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Commonsense Reasoning on HellaSwag IID distribution
Loading...
77.82
Accuracy
FedAlign-MoE
71.476
73.123
74.77
76.417
Mar 22, 2026
Accuracy
Updated 25d ago
Evaluation Results
Method
Method
Links
Accuracy
FedAlign-MoE
Model=DeepSeek-MoE-16B
2026.03
77.82
FedMoE
Model=DeepSeek-MoE-16B
2026.03
76.11
FedAlign-MoE
Model=Switch-base-16
2026.03
75.31
PFL-MoE
Model=DeepSeek-MoE-16B
2026.03
75.08
FedMoE
Model=Switch-base-16
2026.03
74.46
FedProx
Model=DeepSeek-MoE-16B
2026.03
74.23
FedAvg
Model=DeepSeek-MoE-16B
2026.03
73.56
PFL-MoE
Model=Switch-base-16
2026.03
73.14
FedProx
Model=Switch-base-16
2026.03
72.04
FedAvg
Model=Switch-base-16
2026.03
71.72
Feedback
Search any
task
Search any
task