List your company

Human Behavior Modeling on CVABench (test)

0.07Media Linguistic TTRQwen2.5-7B-SFT+DPO
0.03880.04690.0550.0631Apr 7, 2026

Evaluation results

MethodLinks
Qwen2.5-7B-SFT+DPOBackbone=Qwen2.5-7B, Training Mode=SFT+DPO2026.040.0743330.0452232.9627.98
Role-Play AgentBackbone=GPT-4o-mini, Training Mode=Training-free2026.040.0635360.074052.8710.29
Reasoning Agent - 0Backbone=GPT-4o-mini, Training Mode=Training-free2026.040.0636350.083842.897.06
Reasoning Agent - 2Backbone=GPT-4o-mini, Training Mode=Training-free2026.040.0643380.063122.87-35.31
Reasoning Agent - 4Backbone=GPT-4o-mini, Training Mode=Training-free2026.040.0642380.063122.88-40.74
Qwen2.5-7B SFTBackbone=Qwen2.5-7B, Training Mode=SFT2026.040.0643330.0452233.0418.68
CVA (Ours)Backbone=Qwen2.5-7B2026.040.0447360.0353322.771.06