SP-Bench
Benchmarks
TaskDatasetSOTA resultTrendResults
SP-Bench Average
68.9Execution Success Rate
7
SP-Bench Challenging
33.3Execution Success Rate
7
SP-Bench Advanced
61.9Execution Success Rate
7
SP-Bench Intermediate
84.5Execution Success Rate
7
SP-Bench Basic
95.8Execution Success Rate
7