Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Benchmark details loading
Back to benchmarks
Blocker deception rate (without developer prompt)
Safety
Share
Official website
Same adversarial blocker-disclosure evaluation without the developer prompt; the only subset published for all four compared models. Replaces the earlier CodingDeception evaluation.
Ranking
Sources
#
Model
Score
1
GPT-6 Astra
OpenAI
11.1
%
2
GPT-6.1 Sol
OpenAI
14.0
%
3
GPT-6.2 Astra
OpenAI
22.3
%
4
GPT-6.2 Sol
OpenAI
24.1
%
4 models total