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

TS-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Safety detectionTS-Bench AgentDojo-Traj (eval)
Efficiency (s/sample)1.36
4
Safety detectionTS-Bench AgentHarm-Traj (eval)
Latency (s/sample)1.36
4
Safety risk detectionTS-Bench
Overall F1 Score86
3
Showing 3 of 3 rows