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

Scientific Reasoning on GPQA-D (Pass@1, #Tok)

68.2Pass@1 Accuracy

DyCon

37.20845.25453.361.346Jun 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
68.26,205
2026.06
67.77,732
2026.06
67.75,699
2026.06
66.29,210
2026.06
65.26,180
2026.06
65.17,654
2026.06
475,304
2026.06
38.47,518