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

Mathematical Reasoning on AQUA-RAT

69.7Accuracy

CoK + SC

20.50833.27946.0558.821May 24, 2022Jan 2, 2023Aug 13, 2023Mar 23, 2024Nov 1, 2024Jun 12, 2025Jan 22, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2023.06
69.7
2023.06
66.8
2023.06
65
2023.06
60.2
2026.01
59.06
2026.01
59.06
2026.01
58.4
2023.06
56.5
2026.01
55.12
2023.06
55.1
2024.03
54.724
2024.03
54.724
2026.01
54.72
2024.03
54.331
2024.03
52.756
2024.03
52.362
2026.01
51.97
2026.01
51.97
2022.05
48.3
2022.05
46.5
2026.01
44.88
2026.01
42.13
2026.01
41.34
2026.01
40.94
2026.01
40.94
2026.01
40.16
2026.01
38.58
2026.01
37.93
37.9
2023.06
37.8
2026.01
37.4
2023.06
36.5
2022.05
36.1
2026.01
35.83
2022.05
35.8
2023.06
35.8
2023.06
33.5
2024.06
31.89
2026.01
31.89
2026.01
31.49
2026.01
31.1
2024.06
30.31
2024.06
29.92
2024.06
29.92
2024.06
29.53
2026.01
29.53
2024.06
29.13
2026.01
28.74
2026.01
28.74
2026.01
28.35
2024.06
27.95
2024.06
27.95
2024.06
26.77
2024.06
24.8
2023.06
24.8
2022.05
23.4
2023.06
22.4