List your company

Language Model Evaluation on Open LeaderBoard v2

0.6547ASAgentSociety
0.61570.6258250.635950.646075May 25, 2026

Evaluation results

MethodLinks
AgentSocietyAgents=6, Domains=152026.050.65470.57148.330.6565
AgentSocietyAgents=6, Domains=15, Train ratio=30%2026.050.65470.57148.330.6565
AgentSocietyAgents=6, Domains=15, Train ratio=25%2026.050.6510.57147.960.6565
AgentSocietyAgents=6, Domains=15, Train ratio=20%2026.050.63930.57146.790.6565
AgentSocietyAgents=6, Domains=15, Train ratio=10%2026.050.61720.57144.580.6565