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

Arithmetic Reasoning on AQUA

77.1Accuracy

DUP

15.32431.36247.463.438Mar 21, 2022Nov 14, 2022Jul 10, 2023Mar 4, 2024Oct 28, 2024Jun 23, 2025Feb 16, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2024.04
77.1--
2024.04
75.5--
2024.04
72.8--
2024.04
71.6--
2024.04
60.2--
2024.04
57.4--
2024.04
55.9--
2024.04
55.9--
2024.04
54.3--
2024.04
53--
2022.03
52--
2026.02
50--
2022.03
48.3--
2026.02
42.91--
2026.02
41.34--
2022.03
39.8--
2026.02
39.37--
2026.02
38.98--
37.9--
2022.10
36.5--
2022.10
35.8--
2022.03
35.8--
2022.10
33.5--
2022.03
26.9--
2022.03
26.8--
2022.03
25.6--
2022.10
24.8--
2022.03
23.6--
2022.10
22.4--
2022.03
18.9--
2022.03
17.7--
2025.07
-21.721.7
2025.07
-25.626
2025.07
-27.624.8
2025.07
-2626.8
2025.07
-27.222.8
2025.07
-46.946.9
2025.07
-47.247.2
2025.07
-48.450.4
2025.07
-5049.2
2025.07
-4851.6
2025.07
-32.332.3
2025.07
-36.238.6
2025.07
-3938.2
2025.07
-37.433.5
2025.07
-41.337.8