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

Complex Reasoning on BBH

90.5Accuracy

DECENTMEM

6.010427.945249.8871.8148May 27, 2025Jul 25, 2025Sep 23, 2025Nov 22, 2025Jan 21, 2026Mar 22, 2026May 21, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.05
90.5
2026.05
89.2
2025.05
85.93
2026.05
85.07
2026.05
84.3
2026.05
82.09
2026.05
81.68
2026.05
79.28
2026.05
76.19
2026.05
76.12
2026.02
76.1
2026.05
72.43
2026.02
72.3
2026.05
71.14
2026.02
70.5
2026.05
68.86
2026.05
68.52
2026.05
67.33
2026.05
66.84
2026.05
65.52
2026.05
65.48
2026.05
65.28
2026.02
64.8
2025.05
64.58
2026.05
63.8
2026.02
63.5
2025.05
63.26
2026.05
62.18
2026.02
62.1
2026.05
61.88
2026.05
61.58
2026.05
61.53
2026.02
60.86
2026.05
60.52
2026.02
60.2
2026.05
59.61
2026.02
59.5
2026.05
59.43
2026.05
58.62
2026.02
57.8
2026.05
57.14
2026.02
54.7
2026.05
54.68
2026.05
54.19
2026.05
53.37
2026.05
52.19
2026.02
51.3
2026.02
50.33
2026.05
48.92
2026.01
48.7
2026.05
48.14
2026.01
47.8
2026.01
47.6
2026.02
47.54
2026.02
45.25
2026.05
45.23
2026.05
44.73
2026.05
44.43
2026.05
43.97
2026.05
42.61
2026.05
42.11
2026.05
41.17
2026.02
41
2026.05
40.86
2026.01
40.55
2026.02
40.06
2026.01
40.02
2026.01
40.02
2026.01
39.78
2026.01
39.56
2026.02
38.22
2026.05
35.13
2026.02
34.42
2026.01
33.99
2026.05
33.67
2026.01
33.37
2026.01
32.78
2026.02
32.72
2026.01
32.11
2026.02
30.24
2026.05
28.13
2026.01
26.26
2025.05
10.85
2025.05
9.38
2025.05
9.26