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

Reasoning & General on IMO-AnswerBench

86.3Score

GPT-5.2 (xhigh)

18.554436.142253.7371.3178Feb 17, 2026Mar 12, 2026Apr 4, 2026Apr 27, 2026May 20, 2026Jun 12, 2026Jul 6, 2026
Updated 18d ago

Evaluation Results

MethodLinks
86.3
83.3
2026.02
82.5
2026.02
82
2026.02
81.8
2026.07
81.1
2026.06
79.53
78.5
78.3
65.81
2026.07
59.9
54.28
2026.06
52.56
2026.07
51.5
2026.06
46.66
2026.06
44.75
2026.06
39.34
2026.06
38.59
2026.06
21.16