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

Sentence Completion on HellaSwag DE

59.6Normalized Log Accuracy

HATified

53.25654.90356.5558.197Mar 16, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
59.66.5
2026.03
53.53.67