IMO-AnswerBench
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
IMO-AnswerBench 50
40.5Pass@1 Accuracy
68
IMO-AnswerBench
93.71Accuracy
45
IMO-AnswerBench
86.3Score
19
IMO-ANSWERBENCH
89.3Score
18
IMO-AnswerBench
83.8Accuracy
16
IMO-AnswerBench
83.3Pass@1
12
IMO-AnswerBench (full)
22.8NComm
10
IMO-AnswerBench
89.8Avg@8
7
IMO-AnswerBench (held-out)
37.85Pass@1 Score
6
IMO-AnswerBench
25.62Pass@1
6
IMO-AnswerBench (test)
25.62Pass@1
4