CL-Bench
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
CL-bench (test)
25.8Overall Score (%)
16
CL-Bench
25.2Score
9
CL-Bench
25.2Score
8
Filtered CL-Bench (test)
34.96Accuracy (DK)
8
CL-Bench (unfiltered)
6.49DK Score
8
CL-Bench (test)
12.85Overall Score
8
CL-bench (test)
26Solve Rate
6
CL-Bench
15.8Overall Score
5
CL-Bench
15.5Pass@1
3