Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multilingual Language Understanding on HellaSwag, ARC-C, XNLI, and MMLU (French Translated Test Set)

57.83HellaSwag Accuracy

GenKnowSub

55.2355.90556.5857.255May 16, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.05
57.8342.9553.6536.1347.64
2025.05
57.6734.5650.7533.3344.08
2025.05
57.4235.9152.4233.2544.75
2025.05
57.0840.2750.1735.3345.71
2025.05
57.0842.6252.9235.5847.05
2025.05
56.4242.2846.3335.5845.15
2025.05
56.0841.9550.6636.6946.34
2025.05
55.3341.6144.3834.7944.02