AMC23
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
AMC23
98.6Pass@k
35
AMC23
53.75Average Score @16
18
AMC23 decontaminated
69.8Accuracy
14
AMC23
91.4Average Score @32
14
AMC23
83.2Accuracy
12
AMC23
79.45Peak avg@32 Score
6
AMC23
10.9Full Length
4