RankingSandbox Bench · September2026 internal
Sandbox Bench · September2026 internal
- Bucket
- Supporting evidence
- Unit
- percent
- Direction
- Higher is better
- Version
- September2026 internal
- Display harness
- GPT-6 Astra System Card
- Board
- https://deploymentsafety.openai.com/gpt-6-astra
The available records have no admitted matched comparison in the capability core. Raw results remain available below.
Compare published benchmark results with category weights →
Models
| Model | Score | Harness | Evidence | Source-recorded date |
|---|---|---|---|---|
| GPT-6 AstraOpenAI | 45.5%Reported settings & source22 isolated CTF-style targets; protected-flag success metric Provider-published result; preserves source setting without claiming a controlled cross-provider comparison. GPT-6 Astra System Card · Section10.1.2.4 · reviewed 2026-09-06 | GPT-6 Astra System Card | lab self-report | 2026-09-06 |
| GPT-5.6 SolOpenAI | 4.5%Reported settings & source22 isolated CTF-style targets; protected-flag success metric Provider-published result; preserves source setting without claiming a controlled cross-provider comparison. GPT-6 Astra System Card · Section10.1.2.4 · reviewed 2026-09-06 | GPT-6 Astra System Card | lab self-report | 2026-09-06 |