Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM-generated text detection on Xsum, WritingPrompts, and SQuAD (Gemini-1.5-Flash test set)
Loading...
75.14
AUROC
SurpMark
43.2848
51.5549
59.825
68.0951
Oct 8, 2025
AUROC
Updated 21d ago
Evaluation Results
Method
Method
Links
AUROC
SurpMark
Black-box setting=true...
2025.10
75.14
SurpMark
Black-box setting=true...
2025.10
74.57
Binoculars
Black-box setting=true
2025.10
74.51
Fast-DetectGPT
Black-box setting=true
2025.10
72.49
Lastde++
Black-box setting=true...
2025.10
71.72
R-Detect
Black-box setting=true
2025.10
69.25
DetectGPT
Black-box setting=true...
2025.10
69.19
DetectNPR
Black-box setting=true...
2025.10
64.96
DNA-GPT
Black-box setting=true...
2025.10
62.06
FourierGPT
Black-box setting=true
2025.10
61.25
Entropy
Black-box setting=true
2025.10
58.36
Likelihood
Black-box setting=true
2025.10
56.49
LogRank
Black-box setting=true
2025.10
53.87
Lastde
Black-box setting=true
2025.10
48.13
DetectLRR
Black-box setting=true
2025.10
44.51
Feedback
Search any
task
Search any
task