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

Mathematical Reasoning on AQUA

85.05Accuracy

OFA-MAS (fine-tuned)

51.728460.379269.0377.6808Apr 19, 2023Oct 21, 2023Apr 24, 2024Oct 27, 2024May 1, 2025Nov 3, 2025May 8, 2026
Updated 13d ago

Evaluation Results

MethodLinks
2026.01
85.05-
2026.01
83.49-
2026.01
83.18-
2026.02
82.6-
2026.01
81.6-
81.1-
2026.01
80.94-
2025.02
80.63-
2026.01
80.51-
79.9-
2023.04
79.92.2913
2026.02
79.4-
2026.03
79.13-
2026.02
79.1-
2026.02
78.5-
2026.02
78.2-
2026.01
77.65-
2023.04
77.5-
2026.02
77.5-
2026.02
77.3-
2024.05
76.9-
2026.02
76.9-
2026.02
76.8-
2025.02
76.77-
2025.02
76.77-
2026.01
76.48-
2024.10
76.4-
2023.04
76.4-
2025.02
76.38-
2026.02
76.2-
2026.02
76.1-
2026.02
75.7-
2026.01
75.63-
2026.02
75.1-
2025.02
75.04-
2025.06
74.8-
2026.05
74.76-
2026.02
74.7-
2025.06
74.4-
2026.03
74.37-
2026.01
74.05-
2026.02
73.9-
2026.03
73.62-
2026.01
73.58-
2026.01
72.95-
2026.02
72.9-
2025.06
72.8-
2026.02
71.3-
2026.01
71.23-
2026.01
71.06-
70.8-
2026.03
70.47-
2026.02
70.4-
2025.02
70.16-
2025.02
70-
2026.02
69.6-
2025.02
68.5-
2026.05
67.52-
2026.03
67.32-
2026.03
66.54-
2024.05
65.4-
2025.06
65.4-
2024.05
64.6-
2026.05
64.02-
2026.03
63.78-
2026.05
63.78-
2026.03
62.99-
2026.05
62.99-
2024.05
62.2-
2024.05
62.2-
2026.03
61.81-
2026.05
61.81-
2024.05
60.6-
2024.10
60.6-
2023.04
60.62.3228
2026.05
60.39-
2026.05
60.16-
2026.05
59.92-
2026.05
59.65-
2026.05
59.45-
2024.05
59.4-
2024.07
59.4-
2026.03
58.23-
2024.05
57.5-
2023.04
57.4-
2024.07
57.1-
2026.03
57.09-
2025.02
56.3-
2024.05
55.9-
2025.02
55.83-
2026.03
55.82-
2025.02
55.28-
2024.05
55.1-
2026.03
54.72-
2025.02
54.65-
2024.05
53.9-
2024.07
53.9-
2025.02
53.15-
2024.07
53.1-
2026.03
53.01-
Showing 100 of 167 rows