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

Math Reasoning on GSM Hard

82.6Accuracy

IPOMP

-0.215221.284942.78564.2851Jan 7, 2026Jan 30, 2026Feb 22, 2026Mar 17, 2026Apr 9, 2026May 2, 2026May 25, 2026
Updated 7d ago

Evaluation Results

MethodLinks
2026.04
82.6--
2026.04
82.2--
2026.04
81.8--
2026.04
81.1--
2026.04
81.1--
2026.04
80.7--
2026.04
80.7--
2026.04
80.3--
2026.04
80.3--
2026.04
79.9--
2026.04
79.9--
2026.04
79.9--
2026.04
79.5--
2026.04
79.2--
2026.04
78--
2026.04
78--
2026.04
76.1--
2026.04
75.4--
2026.04
72.7--
2026.04
70.5--
2026.04
69.4--
2026.04
69.4--
2026.04
69.4--
2026.04
68.9--
2026.04
68.6--
2026.04
68.6--
2026.04
68.6--
2026.04
68.6--
2026.04
68.6--
2026.04
68.2--
2026.04
67.5--
2026.05
67.37-2,747.7
2026.01
66.9--
2026.04
66.7--
2026.04
66.7--
2026.04
66.4--
2026.04
65.6--
2026.01
64.9--
2026.01
64.4--
2026.05
64.03-3,125.8
2026.01
63.5--
2026.01
62.9--
2026.01
62.4--
2026.01
61.6--
2026.01
61.5--
2026.01
60.7--
2026.01
60--
2026.01
59--
2026.05
57.14-292.8
2026.01
56.1--
2026.01
56--
2026.01
55.4--
2026.05
55.05-14,186.4
2026.01
53.5--
2026.01
53.4--
2026.01
53.1--
2026.05
51.44-4,372.5
2026.01
50.7--
2026.05
48.87-206.7
2026.04
48.1--
2026.01
43.6--
2026.01
43.4--
2026.01
40.8--
2026.01
38.7--
2026.01
38.3--
2026.01
35.6--
2026.01
33--
2026.01
31.7--
2026.01
8.274.12-
2026.01
6.237.01-
2026.01
4.866-
2026.01
3.870-
2026.01
2.976-