List your company

Steering Validation on Synthetic Stubs Comparison Phase 1

96.7Haiku Judge AccuracyDACS
36.3852.0467.783.36Apr 9, 2026

Evaluation results

MethodLinks
DACSN=3, Scenario=s1_n32026.0496.705610.0001
DACSN=5, Scenario=s2_n52026.0496.706330.0001
BaseN=3, Scenario=s1_n32026.0460—1,1910.0001
BaseN=5, Scenario=s2_n52026.0438.7—1,7200.0001