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

Mathematical Reasoning on AGIEval MATH (Accuracy)

95.7Accuracy

UPA

9.69232.02154.3576.679Sep 28, 2025Nov 4, 2025Dec 11, 2025Jan 18, 2026Feb 24, 2026Apr 2, 2026May 10, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2026.01
95.7--
2026.01
95.3--
2026.01
94.9--
2026.01
94.8--
2026.05
93.3--
2026.05
93.3--
2026.01
93.1--
2026.01
91.7--
2026.01
89.5--
2026.05
88.1--
2026.05
87.9--
2026.01
86.6--
2026.01
86.3--
2026.01
86.2--
2026.01
85.9--
2026.01
84.7--
2026.05
80.9--
2026.05
76.3--
2026.04
75.6--
2026.05
73.7--
2026.05
73.6--
2026.05
73.6--
2026.05
73.4--
2025.09
73.4--
2026.05
72.9--
2026.05
72.4--
2026.04
71.3--
2026.04
70.6--
2025.09
70.4--
2026.04
68.7--
2026.05
68.1--
2026.04
67.8--
2026.05
66.6--
2026.05
65.4--
2025.09
64.5--
2026.04
64.1--
2026.05
64--
2026.05
62.8--
2026.04
61.1--
2026.05
59.7--
2025.09
59.2--
2026.04
58.9--
2025.09
54.9--
2026.05
54.7--
2026.04
54--
2026.04
53.4--
2026.04
52.4--
2026.04
52.3--
2026.04
51.9--
2026.04
50.7--
2025.09
50.1--
2026.04
49.9--
2026.04
47.565-
2026.04
46.9--
2026.04
46.768.6-
2026.04
46.166.6-
2026.04
46.166.9-
2026.04
45.964.5-
2026.05
45.6-73.6
2026.04
45.262.3-
2026.05
45.1-78.2
2026.04
44.966.3-
2026.04
44.563.8-
2026.04
44.464.8-
2026.04
44.463.9-
2026.04
44.264.8-
2026.04
44.266-
2026.04
44.161.4-
2026.04
4463.9-
2026.04
43.862.2-
2026.04
43.564-
2026.04
43.363.1-
2026.04
42.962.4-
2026.04
42.961.4-
2026.04
42.661.2-
2026.04
42.561.7-
2026.04
42.161.6-
2026.04
42.161.1-
2026.04
42.161.6-
2026.04
4260.4-
2026.04
41.860.9-
2026.04
41.465-
2026.04
40.762.7-
2026.04
40.358.8-
2026.04
40.259.2-
2026.04
40.162-
2026.04
39.857.93-
2026.04
39.658.2-
2026.05
38.5-72.3
2026.05
36.2-67.3
2026.05
35.8-65
2026.05
33.1-65.5
2026.05
27.6-58.6
2026.05
26.5--
2026.05
25.1-57.3
2026.05
19.3-50.3
2026.05
18.5-51.8
2026.05
15.1-38.2
2026.05
13-43.2