List your company

CBT-specific skills evaluation on 150 randomly sampled instances (test)

4.85Guided Discovery ScoreCCD-CBT
4.36124.48814.6154.7419Apr 8, 2026

Evaluation results

MethodLinks
CCD-CBTEvaluator=Gemini-3-Flash2026.044.855.265.34
CamelEvaluator=Gemini-3-Flash2026.044.785.034.9
SoulChat2.0Evaluator=Gemini-3-Flash2026.044.384.824.48