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

General Queries

Benchmarks

Task NameDataset NameSOTA ResultTrend
Deployment Cost AnalysisGeneral Queries
Peak Memory (GB)79.5
6
RefusalGeneral queries off-topic (test)
Avg Appearance Score0.91
2
Tool UseGeneral queries off-topic (test)
Average Appearance Score52
2
AbstentionGeneral queries off-topic (test)
Average Appearance Score68
2
Showing 4 of 4 rows