Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Arithmetic Reasoning on SVAMP

93.7Accuracy (Overall)

Automatic Model Selection with LLMs

6.75629.32851.974.472Jan 28, 2022Aug 2, 2022Feb 4, 2023Aug 9, 2023Feb 11, 2024Aug 15, 2024Feb 18, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2023.05
93.7--
2023.05
92.2--
2023.05
91.9--
2025.02
86--
2023.05
84.3--
2023.05
83--
2025.02
82.6--
2023.05
82.2--
2023.05
80.3--
2022.01
79.8--
2023.05
79.6--
2022.01
79--
2025.02
78.8--
2023.05
77.6--
2025.02
77.3--
2022.01
77--
2022.01
76.4--
2025.02
76.3--
2025.02
75--
2025.02
74.9--
2025.02
73.8--
2025.02
73.2--
2022.01
70.3--
2025.02
70.2--
2025.02
70--
2022.01
69.9--
2022.01
69.4--
2025.02
69.2--
2022.01
68.9--
2025.02
67.2--
2025.02
66.9--
2022.01
65.7--
2025.02
65.4--
2025.02
65--
2025.02
64.5--
2025.02
63.6--
2025.02
60.4--
2025.02
60--
2025.02
59.9--
2025.02
59.2--
2025.02
58.2--
2022.01
57.4--
2025.02
50.8--
2025.02
49.5--
2022.01
42.1--
2022.05
41.4--
2022.01
37.5--
2022.01
29.5--
2022.01
28.3--
2022.05
28.3--
2022.01
12.5--
2022.05
12.5--
2022.01
10.1--
2022.05
10.1--
2025.07
-52.252.2
2025.07
-53.452.6
2025.07
-52.453.4
2025.07
-52.553.3
2025.07
-52.352.5
2025.07
-74.274.2
2025.07
-75.576.1
2025.07
-77.177.9
2025.07
-7878.1
2025.07
-75.274.8
2025.07
-67.467.4
2025.07
-65.966.2
2025.07
-66.365.3
2025.07
-70.370.6
2025.07
-6666.9