List your company

Role Clarity on SWE easy (dev)

0.9081Role Clarity ScoreChatDev
0.4836760.5938630.704050.814237Apr 3, 2026

Evaluation results

MethodLinks
ChatDevCEO=FT, CPO=FT, Backbone=Qwen, Role clarity regularization=Enabled2026.040.90810.3721
ChatDevCEO=FT, CPO=FT, Backbone=Llama, Role clarity regularization=with2026.040.85250.3525
ChatDevCEO=FT, CPO=Base, Backbone=Qwen, Role clarity regularization=Enabled2026.040.65830.1223
ChatDevCEO=Base, CPO=FT, Backbone=Qwen, Role clarity regularization=Enabled2026.040.60140.0654
ChatDevCEO=FT, CPO=Base, Backbone=Llama, Role clarity regularization=with2026.040.59750.0975
ChatDevCEO=Base, CPO=FT, Backbone=Llama, Role clarity regularization=with2026.040.56350.0635
ChatDevCEO=Base, CPO=Base, Backbone=Qwen, Role clarity regularization=Enabled2026.040.536—
ChatDevCEO=Base, CPO=Base, Backbone=Llama, Role clarity regularization=with2026.040.5—