benchmaxxer Sep 23, 2026
Advanced Screening EvasionBrowse 296

Advanced Screening Evasion

Can the model reason accurately about difficult scientific material?

Latest stableGPT-6 Astra System Card · SecureBio helpful-only checkpoint
Science2 ranked models2 reported values1 reportsHigher is better

Top rankings

One row per model, using its best reported score across effort settings.

2
RankModelBest scoreBest reported setting
1GPT-6 AstraOpenAI0.728Reported configurationOpenAI report1 value · 1 reportSep 3, 2026 · source
2GPT-5.6 SolOpenAI0.726Reported configurationOpenAI report1 value · 1 reportSep 3, 2026 · source

Effort curve

Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.

0
No cost-linked effort sweep for this version.
Definition and comparison boundaryinternal methodology

Can the model reason accurately about difficult scientific material?

Scientific knowledge and reasoning under the benchmark's published question set. Higher is better. Score reported by OpenAI for the helpful-only checkpoint.

This is a publisher-defined internal evaluation. The task set or grading details are not fully public, so treat it as directional evidence.

OpenAI reports 0.728 for the helpful-only Astra checkpoint versus 0.726 for the helpful-only GPT-5.6 Sol checkpoint; SecureBio identified efficiency and reliability concerns and practical feasibility remains uncertain.

Method / source