Text-only Adaptive Benchmark
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Text-only Adaptive Benchmark (ALL)
81Pass@1 Acc
5
Text-only Adaptive Benchmark L5
65Pass@1 Accuracy
5
Text-only Adaptive Benchmark L4
81Pass@1 Accuracy
5
Text-only Adaptive Benchmark L3
88Pass@1 Accuracy
5
Text-only Adaptive Benchmark L1
93Pass@1 Accuracy
5