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

IMO-AnswerBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Math ReasoningIMO-AnswerBench 50
Pass@1 Accuracy40.5
68
Mathematical ReasoningIMO-AnswerBench
Accuracy93.71
45
Reasoning & GeneralIMO-AnswerBench
Score86.3
19
MathIMO-ANSWERBENCH
Score89.3
18
Mathematical ReasoningIMO-AnswerBench
Accuracy83.8
16
Mathematical ReasoningIMO-AnswerBench
Pass@183.3
12
Multiple-choice Question AnsweringIMO-AnswerBench (full)
NComm22.8
10
ReasoningIMO-AnswerBench
Avg@889.8
7
Mathematical ReasoningIMO-AnswerBench (held-out)
Pass@1 Score37.85
6
Mathematical ReasoningIMO-AnswerBench
Pass@125.62
6
Mathematical ReasoningIMO-AnswerBench (test)
Pass@125.62
4
Showing 11 of 11 rows