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

Multi-task Language Understanding on MMLU-Pro (pass@1)

92.85Pass@1

GT-Reward

6.58228.978551.37573.7715Aug 25, 2025Sep 17, 2025Oct 10, 2025Nov 3, 2025Nov 26, 2025Dec 19, 2025Jan 12, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2025.11
92.85
2025.11
92.85
2025.11
91.42
2025.11
85.71
2025.11
77.68
2025.11
77.58
2025.11
72.85
2025.11
69.91
2025.11
67.68
2025.11
66.16
2025.11
64.55
2025.08
63.65
2025.08
62.61
2025.08
60.92
2025.11
60.54
2025.08
59.18
2025.08
58.98
2026.01
57.8
2025.11
57.59
2026.01
57
2025.08
56.58
2026.01
56.3
2026.01
55.9
2026.01
55.8
2025.08
54.39
2025.11
53.66
2025.11
52.95
2025.11
51.79
2026.01
51.5
2025.08
50.29
2025.11
50.09
2025.11
50
2026.01
49.1
2025.11
47.14
2026.01
45.5
2025.11
45.36
2026.01
45.3
2025.11
44.82
2026.01
44.6
2026.01
44.5
2025.11
44.29
2025.11
43.75
2026.01
43.5
2026.01
43.2
2026.01
43
2025.11
42.77
2026.01
42.4
2026.01
42.2
2026.01
41.3
2025.11
40.8
2025.11
40
2026.01
39.6
2026.01
39.1
2026.01
38.4
2025.11
34.64
2025.11
34.38
2025.11
34.11
2025.11
34.02
2025.11
31.43
2025.11
31.25
2025.11
27.59
2025.11
18.04
2025.11
16.61
2026.01
9.9