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

Social Simulation

Benchmarks

Task NameDataset NameSOTA ResultTrend
Social SimulationSocial Simulation
Configurability3
24
Agent Behavior EvaluationSocial Simulation Family context 1.0
Naturalness4.905
20
Agent Behavior EvaluationSocial Simulation Workplace context 1.0
Naturalness Score4.878
20
Agent Behavior EvaluationSocial Simulation School context 1.0
Naturalness4.958
20
Showing 4 of 4 rows