Sandbox Bench A
AI benchmark · Cybersecurity
- Built by
- OpenAI
- Domains
- Cybersecurity
- Tier
- A why
- Snapshot
What is Sandbox Bench?
Sandbox Bench is an internal OpenAI evaluation of 22 CTF-style challenges testing a model's ability to identify and exploit vulnerabilities in runtimes, file format parsers, and egress proxies.
Security mostly
“Sandbox Bench is a new internal evaluation designed to test a model’s ability to identify and exploit vulnerabilities in runtimes, file format parsers, and egress proxies”
deploymentsafety.openai.com/gpt-6-astra/sandbox-bench ↗
Who built Sandbox Bench
Led by OpenAI.
Tier A
Widely used: a lab reports it, or 50 or more models are scored on it.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- 4 models scored
- reported by OpenAI
- in curated RL directories (1 pt)
How we got to tier A
- Adoption: 4 models scored; reported by OpenAI. Tier A.
- On X: unclear, none buzz No move.
- In curated RL directories: 1 point, a floor of none.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Where Sandbox Bench sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-11-16 snapshot.