Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multilingual Understanding on M-HellaSwag
Loading...
1.014
Performance
Iso-CTS
0.67496
0.76298
0.851
0.93902
Jun 15, 2026
Performance
Updated 1mo ago
Evaluation Results
Method
Method
Links
Performance
Iso-CTS
Category=State-of-the-...
2026.06
1.014
Iso-C
Category=State-of-the-...
2026.06
1.005
TSV-M
Category=State-of-the-...
2026.06
1.005
DARE
Category=Conventional...
2026.06
1.005
FedMerge
Category=Iterative / F...
2026.06
0.991
TULU 3
Category=Data-Mixing,...
2026.06
0.991
TIES
Category=Conventional...
2026.06
0.991
METIS
Category=Ours, Backbon...
2026.06
0.991
ConsensusTA
Category=Conventional...
2026.06
0.981
ColD Fusion
Category=Iterative / F...
2026.06
0.977
TA + Subspace Boosting
Category=State-of-the-...
2026.06
0.963
Task Arithmetic
Category=Conventional...
2026.06
0.953
q-FedAvg
Category=Iterative / F...
2026.06
0.688
Feedback
Search any
task
Search any
task