Hard-negative protein binding predictionBrowse 296

Hard-negative protein binding prediction

Can the model reason accurately about difficult scientific material?

Latest stableGPT-6 Astra System Card · September 2026 retired evaluation
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-5.6 SolOpenAI7.6%Reported configurationOpenAI report1 value · 1 reportSep 3, 2026 · source
2GPT-6 AstraOpenAI0.0%Reported 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. Percentage of protein-binding selections scored correct by OpenAI.

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 0.0% for ordinary Astra and 7.6% for GPT-5.6 Sol on a proprietary non-contaminated evaluation with 43 protein targets and 492 hotspots; a helpful-only Astra model is also 0.0%. OpenAI is retiring this evaluation and notes an environment-variable leakage issue.

Method / source