Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

InterCode

Benchmarks

Task NameDataset NameSOTA ResultTrend
Interactive Decision MakingInterCode NL2Bash
Success Rate79.6
40
interactive SQL queryingInterCode SQL
Avg Reward69.1
10
SQL Code GenerationInterCode SQL
Success Rate7.3
7
Bash Command ExecutionInterCode Bash
Execution Success Rate72
4
Showing 4 of 4 rows