Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text Detectability on GPT-5-pro Experiment 2 averaged over n ∈ {3, ..., 10} 2025-10-06
Loading...
99
BERT Score
Template-based
52.2
64.35
76.5
88.65
Apr 8, 2026
BERT Score
GPT-2 Score
RoBERTa Score
DistilBERT Score
Average Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
BERT Score
GPT-2 Score
RoBERTa Score
DistilBERT Score
Average Score
Template-based
2026.04
99
98
97
99
83
LLM-dependent
2026.04
61
63
62
66
58
LLM+ID
2026.04
59
61
60
64
57
LLM+CA
2026.04
58
60
59
63
56
iTAG
2026.04
54
56
55
59
53
Feedback
Search any
task
Search any
task