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

Language Understanding on MMLU (Category Breakdown Scores)

37.31STEM Accuracy (MMLU)

FP16

26.868429.579232.2935.0008Oct 16, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.10
37.3152.9143.0453.8246.46
2024.10
36.4850.5741.9152.1645
2024.10
36.2548.0739.8349.0743
2024.10
36.2450.3141.7252.2244.85
2024.10
34.5946.0539.6247.7841.83
2024.10
34.1343.8738.1345.5940.25
2024.10
32.5443.2636.3445.9939.27
2024.10
31.7436.5930.8638.0933.98
2024.10
28.2425.6731.6932.9229.85
2024.10
27.9323.6324.8724.1225.08
2024.10
27.2730.8127.0825.5127.57