LLM-generated text detection on HC3 Gemini-3.1 pro preview generated text benchmark leaderboard · SOTA2 Research

LLM-generated text detection on HC3 Gemini-3.1 pro preview generated text

0.813ROC AUCJCASEMCD

Evaluation Results

Method	Links
JCASEMCD2026.07		0.813	0.781	0.754	0.606	0.725	0.682	0.844	0.744
JCELLMCD2026.07		0.748	0.695	0.717	0.6	0.691	0.662	0.783	0.699
LogRank2026.07		0.74	0.707	0.699	0.476	0.647	0.61	0.818	0.671
Rank2026.07		0.71	0.732	0.682	0.734	0.694	0.711	0.654	0.702
Likelihood2026.07		0.698	0.722	0.669	0.015	0.507	0.503	0.998	0.587
DetectGPT-d2026.07		0.518	0.666	0.667	0.001	0.501	0.5	1	0.55
DetectGPT-z2026.07		0.506	0.653	0.667	0	0.5	0.5	1	0.547
Entropy2026.07		0.287	0.377	0.667	0	0.5	0.5	1	0.476
RoBERTa-base2026.07		0.275	0.365	0.667	0.007	0.502	0.501	0.998	0.474
RoBERTa-large2026.07		0.179	0.338	0.667	0	0.5	0.5	1	0.455