Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Abstention Detection on AbstentionBench
Loading...
53
Recall
gpt-5-thinking
43.64
46.07
48.5
50.93
Dec 19, 2025
Recall
Updated 3mo ago
Evaluation Results
Method
Method
Links
Recall
gpt-5-thinking
2025.12
53
OpenAI o3
2025.12
44
Feedback
Search any
task
Search any
task
