List your company

Agent Task Utility and Admission Integrity on Code-agent exact-effect benchmark

231STC CountCXI
219.45225.225231236.775Jul 7, 2026

Evaluation results

MethodLinks
CXIUnit / N=400 repo episodes, Accounting note=73 parse failures; 61 no effect authorization; 35 task-quality failures2026.07231————000736135