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

Multi-task Language Understanding on MMLU (Overall, Stem)

61.08Overall Accuracy

Frozen Router

53.092855.166457.2459.3136Jun 1, 2026
Updated 19h ago

Evaluation Results

MethodLinks
2026.06
61.0853.19
2026.06
61.0553.82
2026.06
61.0353.16
2026.06
61.0352.87
2026.06
60.8552.27
2026.06
54.0446.46
2026.06
53.9746.18
2026.06
53.9546.18
2026.06
53.6945.54
2026.06
53.444.91