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

General and STEM Reasoning on SciBench

71.39Pass@1

MINDLOOM

46.960453.302759.64565.9873May 20, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.05
71.3985.11
2026.05
67.4880.78
2026.05
66.1879.62
2026.05
65.7577.75
2026.05
65.0379.05
2026.05
60.6976.73
2026.05
6078.9
2026.05
57.6676.3
2026.05
57.0873.41
2026.05
56.2168.93
2026.05
54.0569.65
2026.05
53.6171.53
2026.05
53.1767.74
2026.05
52.665.03
2026.05
52.3168.93
2026.05
51.7369.08
2026.05
50.4361.85
2026.05
50.1467.92
2026.05
49.4269.51
2026.05
47.964.9