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

Arithmetic Reasoning on SVAMP (test)

98.16Accuracy

SGE

35.697651.913868.1384.3462May 28, 2024Sep 25, 2024Jan 23, 2025May 24, 2025Sep 21, 2025Jan 19, 2026May 20, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2024.05
98.16
2024.05
92.16
2024.05
91.58
2024.05
91
2026.05
90.4
2026.05
90.1
2026.05
89.8
2026.05
89.3
2026.05
89.2
2025.12
88.8
2026.05
88.5
2025.12
88.4
2024.05
88.34
2026.05
87
2025.12
86.7
2025.12
86.4
2025.12
86.4
2025.12
86.3
2025.12
86.1
2025.12
86
2025.12
85.6
2026.05
85.5
2026.05
85.5
2025.12
85.3
2025.12
85.3
2025.12
85.2
2026.05
84.8
2025.12
84.7
2026.05
84.6
2026.05
83.9
2026.05
83.9
2026.05
83.7
2025.12
83.4
2026.05
83.2
2025.12
82.7
2025.12
82.6
2025.12
81.3
2026.05
80.6
2025.12
80.1
2025.12
78.1
2025.12
77.5
2025.12
77.4
2025.12
77.2
2025.12
76.5
2025.12
75.7
2025.12
70.1
2025.12
69.9
2025.12
68.2
2025.12
66.7
2025.12
66.4
2025.12
66
2025.12
65.8
2025.12
65.7
2024.08
59.5
2024.08
58.3
2024.08
57.3
2024.08
55.7
2024.08
54.6
2024.08
54.2
2024.08
52.3
2024.08
52.1
2024.08
50.8
2024.08
49.6
2024.08
49.4
2024.08
49.3
2024.08
48.5
2024.08
46.8
2024.08
46.7
2024.08
41.4
2024.08
38.1