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

Complex Reasoning on BBH (val)

65.81Accuracy

G2IS

53.413256.631659.8563.0684Feb 16, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.02
65.81
2025.02
65.01
2025.02
64.6
2025.02
64.05
2025.02
63.74
2025.02
63.69
2025.02
63.69
2025.02
63.52
2025.02
63.46
2025.02
63.4
2025.02
63.23
2025.02
62.4
2025.02
61.36
2025.02
61.36
2025.02
61.05
2025.02
60.82
2025.02
60.74
2025.02
60.57
2025.02
60.18
2025.02
60.07
2025.02
59.35
2025.02
59.07
2025.02
58.93
2025.02
58.65
2025.02
58.45
2025.02
58.29
2025.02
58.09
2025.02
58.04
2025.02
56.87
2025.02
56.7
2025.02
56.58
2025.02
56.54
2025.02
56.37
2025.02
56.14
2025.02
56.09
2025.02
56.01
2025.02
55.64
2025.02
55.55
2025.02
55.24
2025.02
54.58
2025.02
54.29
2025.02
53.89