Share your thoughts, 1 month free Claude Pro on usSee more

LLM-generated text detection

Benchmarks

Dataset Name	SOTA Method	Metric
EvoBench	DetectRouter	LLaMA3 Score95.66	26	4mo ago
NLPCC Shared Task 1 2025 (test)	EnsemJudge	Macro F1 (All Lengths)99.22	19	3mo ago
DetectRL Out-of-Domain Multi-Topic 1.0 (test)	Binoculars + MoP	Average Detection Score91.1	18	3mo ago
WP-s Claude3 Opus	ReMoDetect	TPR @ FPR 1%96	18	4mo ago
XSum Claude3 Opus	ReMoDetect	TPR @ FPR 1%97.3	18	4mo ago
PubMed Claude3 Opus	ReMoDetect	TPR @ FPR 1%62.7	18	4mo ago
WP-s GPT4 Turbo	ReMoDetect	TPR @ FPR 1%98.7	18	4mo ago
XSum GPT4 Turbo	ReMoDetect	TPR @ FPR 1%99.3	18	4mo ago
PubMed GPT4 Turbo	ReMoDetect	TPR at FPR 1%67.3	18	4mo ago
WP-s GPT4	ReMoDetect	TPR @ FPR 1%82	18	4mo ago
XSum GPT4	ReMoDetect	TPR @ FPR 1%79.3	18	4mo ago
PubMed GPT4	ReMoDetect	TPR at FPR 1%70	18	4mo ago
WP-s GPT3.5 Turbo	ReMoDetect	TPR at FPR 1%97.3	18	4mo ago
XSum GPT3.5 Turbo	ReMoDetect	TPR @ FPR 1%96.7	18	4mo ago
PubMed GPT3.5 Turbo	ReMoDetect	TPR @ FPR 1%63.3	18	4mo ago
DetectRL Out-of-Domain Multi-LLM 1.0 (test)	Binoculars + kNNProxy	Average Performance Score90.6	16	3mo ago
Xsum, WritingPrompts, and SQuAD Aggregated (test)	Lastde++	GPT2-XL99.46	15	2mo ago
Xsum, WritingPrompts, and SQuAD generated by GPT-5-Chat (test)	SurpMark	AUROC81.33	15	2mo ago
Xsum, WritingPrompts, and SQuAD generated by GPT-4.1-mini (test)	SurpMark	AUROC80.25	15	2mo ago
Xsum, WritingPrompts, and SQuAD Gemini-1.5-Flash (test)	SurpMark	AUROC75.14	15	2mo ago
Yelp Review Dataset	DSIPA (SDP)	F1 (Original)89.8	12	2mo ago
Reuter News Dataset	DSIPA (SDP)	F1 (Original)89.2	12	2mo ago
DetectRL	IRM	AUROC (Multi-Domain)97.97	12	2mo ago
HART (default random split)	RACE	Avg TPR @ 5% FPR94.41	12	3mo ago
KatFish Paper Abstract	KatFishNet	AUC-ROC (Solar)78.99	12	4mo ago

Showing 25 of 120 rows