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

Reasoning on MGSM

90Accuracy

RoT

74.478.4582.586.55Oct 16, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.10
90
2024.10
88.7
2024.10
87.9
2024.10
87.5
2024.10
86.7
2024.10
86.3
2024.10
85.9
2024.10
85.5
2024.10
85.1
2024.10
84.7
2024.10
84.7
2024.10
84.3
2024.10
83.9
2024.10
82.3
2024.10
82.3
2024.10
81.5
2024.10
81.1
2024.10
81
2024.10
80.3
2024.10
80.3
2024.10
79.4
2024.10
78.3
2024.10
77.4
2024.10
75