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

Question Answering on MMLU-Pro

89.1Accuracy

Reasoningbank

11.297631.496351.69571.8937May 27, 2025Jul 19, 2025Sep 11, 2025Nov 4, 2025Dec 28, 2025Feb 20, 2026Apr 15, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.02
89.1
2026.02
87.9
2026.02
87.3
2026.02
87.2
2026.02
85.8
2026.02
81.6
2026.02
79.4
2026.02
79.1
2026.02
77.8
2026.02
76.8
2026.02
75
2026.02
74.2
2026.02
70.1
2026.02
68.7
2026.04
66.49
2025.05
65.36
2026.04
63.79
2026.04
61.12
2026.04
59.72
2026.04
59.47
2026.04
58.61
2025.09
55.98
2025.09
54.98
2025.09
53.82
2025.09
53.4
2025.09
51.12
2025.09
50.37
2026.02
50.3
2025.09
49.96
2025.09
49.58
2026.02
48.9
2025.05
48.54
2026.02
48.5
2025.09
48.21
2025.09
48.01
2026.02
48
2025.05
47.36
46.36
2025.06
46.23
2025.06
43.01
2025.09
42.31
2025.06
42.3
2025.06
40.89
2025.06
40.74
2025.09
40.31
37.88
37.59
2025.06
37.22
2025.06
36.69
2025.06
36.52
2025.06
36.21
2025.06
35.98
35.49
35.29
34.93
33.73
33.14
2025.06
32.39
2025.06
28.65
2025.05
14.86
2025.05
14.62
2025.05
14.29