LLM-generated text detection on HC3 GPT-5.4 mini generated text benchmark leaderboard · SOTA2 Research

LLM-generated text detection on HC3 GPT-5.4 mini generated text

0.967ROC AUCDetectGPT-d

Evaluation Results

Method	Links
DetectGPT-d2026.07		0.967	0.97	0.919	0.904	0.918	0.906	0.932	0.931
Likelihood2026.07		0.958	0.937	0.929	0.886	0.926	0.895	0.967	0.928
LogRank2026.07		0.954	0.934	0.929	0.893	0.926	0.9	0.96	0.928
DetectGPT-z2026.07		0.952	0.94	0.916	0.885	0.914	0.891	0.943	0.92
JCASEMCD2026.07		0.951	0.955	0.892	0.925	0.895	0.92	0.866	0.915
JCELLMCD2026.07		0.945	0.939	0.887	0.873	0.885	0.876	0.898	0.9
Rank2026.07		0.854	0.825	0.799	0.746	0.79	0.767	0.835	0.802
RoBERTa-large2026.07		0.264	0.363	0.667	0	0.5	0.5	1	0.471
RoBERTa-base2026.07		0.251	0.357	0.667	0	0.5	0.5	1	0.468
Entropy2026.07		0.027	0.309	0.667	0	0.5	0.5	1	0.429