SecureBio Multimodal Troubleshooting VirologyBrowse 284 families
SecureBio Multimodal Troubleshooting Virology
Can the model reason accurately about difficult scientific material?
- Domain
- Science
- Ranked models
- 1
- Reported values
- 1
- Reports
- 1 · lab
- Direction
- Higher is better
- Status
- Latest stable
Rankings
Best reported score per model across effort settings
| # | Model | Best setting | Score |
|---|---|---|---|
| 1 | GPT-6 AstraOpenAI | reportedcost n/a1 value · Sep 3 · source | 55.78% |
Effort curve
Score vs. reported cost. Lines connect complete sweeps only.
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. Refusal-corrected accuracy reported by OpenAI from SecureBio's evaluation.
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 55.78% for the pre-release Astra checkpoint, with a refusal-adjusted score of 63.11%, on 322 SecureBio virology troubleshooting questions; the values are not from the helpful-only checkpoint.
Method / source ↗