Machine-generated text detection

Benchmarks

Dataset Name	SOTA Method	Metric
MGT benchmark Essay	ReMoDetect	AUROC100	129	4d ago
TruthfulQA	DetectGPT-E	TPR@FPR-1%94.85	48	4d ago
MGT benchmark Reuters	Fast-DetectGPT	AUROC100	45	4d ago
Reuters (Claude)	DNA-GPT-M	TPR @ FPR=1%85.2	36	4d ago
Reuters GPT4All	DNA-GPT-M	TPR @ FPR=1%93.24	36	4d ago
Grover (test)	PECOLA	Accuracy73.12	36	4d ago
M4	Likelihood	TP @ 20%87.28	32	4d ago
SemEval (test)	F.t.XLM-RoBERTa-Base	ASR66.2	26	4d ago
Reuters ChatGPT-turbo	DNA-GPT-M	TPR@FPR=1%97.51	24	4d ago
Reuters ChatGLM	DNA-GPT-M	TPR@FPR=1%99.29	24	4d ago
Reuters Dolly	Likelihood-M	TPR @ FPR=1%38.62	24	4d ago
Reuters ChatGPT split	DNA-GPT-M	TPR@FPR=1%98.09	24	4d ago
Essay ChatGPT-turbo (test)	Likelihood-M	TPR@FPR=1%94.36	24	4d ago
Essay Claude (test)	DNA-GPT-M	TPR @ FPR=1%0.4471	24	4d ago
Essay ChatGLM (test)	DNA-GPT-M	TPR@FPR=1%99.55	24	4d ago
Essay Dolly (test)	DNA-GPT-M	TPR@FPR=1%72.6	24	4d ago
Essay (ChatGPT) (test)	DNA-GPT-M	TPR@FPR=1%92.53	24	4d ago
Essay GPT4All (test)	DNA-GPT-M	TPR @ FPR=1%93.58	24	4d ago
Reuters (test)	DNA-GPT-M	TPR@FPR=1%99.87	22	4d ago
MAGE	Binoculars	TP @ 20%85.12	18	4d ago
Essay (test)	Likelihood-M	TPR @ FPR=1%97.1	16	4d ago
MGTBench 2.0	DistillBert-F	F1 Score (Llama-3.1-70b - ST)99.7	14	4d ago
RealDet	Binoculars	TP @ 20% Threshold91.06	14	4d ago
HC3 COLING2025 (val)	RoBERTa-Base-ChatGPT	AUC99.99	13	4d ago
MAGE COLING2025 (val)	RoBERTa-Large-GPT2	AUC79.55	13	4d ago

Showing 25 of 109 rows