Role Clarity on SWE easy (dev)
0.9081Role Clarity ScoreChatDev
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ChatDevCEO=FT, CPO=FT, Backbone=Qwen, Role clarity regularization=Enabled2026.04 | 0.9081 | 0.3721 | |
| ChatDevCEO=FT, CPO=FT, Backbone=Llama, Role clarity regularization=with2026.04 | 0.8525 | 0.3525 | |
| ChatDevCEO=FT, CPO=Base, Backbone=Qwen, Role clarity regularization=Enabled2026.04 | 0.6583 | 0.1223 | |
| ChatDevCEO=Base, CPO=FT, Backbone=Qwen, Role clarity regularization=Enabled2026.04 | 0.6014 | 0.0654 | |
| ChatDevCEO=FT, CPO=Base, Backbone=Llama, Role clarity regularization=with2026.04 | 0.5975 | 0.0975 | |
| ChatDevCEO=Base, CPO=FT, Backbone=Llama, Role clarity regularization=with2026.04 | 0.5635 | 0.0635 | |
| ChatDevCEO=Base, CPO=Base, Backbone=Qwen, Role clarity regularization=Enabled2026.04 | 0.536 | — | |
| ChatDevCEO=Base, CPO=Base, Backbone=Llama, Role clarity regularization=with2026.04 | 0.5 | — |