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

Multi-task Language Understanding on MMLU (Accuracy, Avg.)

84.9Accuracy

DAAO

77.526479.440781.35583.2693Sep 14, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.09
84.983.26
2025.09
84.2580.66
2025.09
83.4280.18
2025.09
83.179.73
2025.09
83.0180.43
2025.09
82.3577.29
2025.09
81.6674.13
2025.09
81.3574.04
2025.09
81.0575.57
2025.09
81.0575.42
2025.09
81.0475.5
2025.09
80.7473.39
2025.09
80.2270.05
2025.09
80.0474.08
2025.09
79.6872.05
2025.09
79.5472.23
2025.09
79.0872.01
2025.09
78.4373.64
2025.09
78.4375.86
2025.09
77.8173.89