Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM-generated content detection on VisualNews
Loading...
0.9746
AUROC
LiSCP
0.4546
0.5896
0.7246
0.8596
May 7, 2026
AUROC
Updated 26d ago
Evaluation Results
Method
Method
Links
AUROC
LiSCP
paraphrase model=GPT-3...
2026.05
0.9746
R-Detect
2026.05
0.965
RAIDAR
2026.05
0.9312
Fast-DetectGPT
2026.05
0.9173
DetectGPT
perturbation model=T5-3B
2026.05
0.8124
Ghostbuster
substitute LLM=GPT-3.5...
2026.05
0.7122
LogRank
2026.05
0.6712
RoBERTa-large
Backbone=large
2026.05
0.5674
Rank
2026.05
0.5412
RoBERTa-base
Backbone=base
2026.05
0.5358
Entropy
2026.05
0.4746
Feedback
Search any
task
Search any
task