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

Math Reasoning on MultiArith (test)

99.59Accuracy

ZERA

82.024486.584791.14595.7053Apr 8, 2026Apr 9, 2026Apr 10, 2026Apr 11, 2026Apr 12, 2026Apr 13, 2026Apr 14, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
99.59
2026.04
99.53
2026.04
99.35
2026.04
99.3
2026.04
98.94
2026.04
98.75
2026.04
98.54
2026.04
98.54
2026.04
98.54
2026.04
98.54
2026.04
98.42
2026.04
98.33
2026.04
98.22
2026.04
98.15
2026.04
98.12
2026.04
97.92
2026.04
97.9
2026.04
97.5
2026.04
97.29
2026.04
96.88
2026.04
96.88
2026.04
96.67
2026.04
96.67
2026.04
96.49
2026.04
96.46
2026.04
96.46
2026.04
96.46
2026.04
95.9
2026.04
95.3
2026.04
95.21
2026.04
95.21
2026.04
93.3
2026.04
92.6
2026.04
91.9
2026.04
91
2026.04
89.9
2026.04
89.8
2026.04
89.7
2026.04
89.5
2026.04
89
2026.04
88.4
2026.04
88.2
2026.04
87.5
2026.04
87.5
2026.04
86.8
2026.04
86.8
2026.04
86.8
2026.04
86.46
2026.04
86.4
2026.04
85.1
2026.04
85.1
2026.04
84.6
2026.04
83
2026.04
82.7