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

Text Generation on MMLU (test)

57.83BS Score

TAP

36.56242.083547.60553.1265Sep 30, 2025
Updated 23d ago

Evaluation Results

MethodLinks
2025.09
57.8340.74
2025.09
55.1640.78
2025.09
54.8739.46
2025.09
54.6739.94
2025.09
46.7521.93
2025.09
46.7113.5
2025.09
46.1613
2025.09
45.7913.02
2025.09
45.5813.37
2025.09
4411.93
2025.09
43.9512.53
2025.09
41.810.81
2025.09
41.677.04
2025.09
41.6320.89
2025.09
40.2920.37
2025.09
40.119.54
2025.09
39.888.91
2025.09
39.3711.05
2025.09
38.348.35
2025.09
37.386.22