List your company

Response Quality Evaluation on ID in-domain (150 samples)

134CountGMM
11.2843.1475106.86Aug 4, 2025

Evaluation results

MethodLinks
GMMClassification Outcome=True Positive (TP)2025.081344.664.754.824.39
GPT-4oClassification Outcome=True Positive (TP)2025.081264.694.734.814.35
GPT-4oClassification Outcome=False Negative (FN)2025.08244.174.564.464.1
GMMClassification Outcome=False Negative (FN)2025.08164.194.344.193.75