Developer Tools
Codex plays NetHack
Last updated 2026-07-27 · benchmark measured 2026-07-27 — deterministic & reproducible
Live asciinema stream of OpenAI Codex autonomously playing NetHack.
Overall production-readiness score — reserved
Legit.Show benchmarked Codex plays NetHack across all seven frames. The single overall score is shown to the verified maker; the frame-by-frame breakdown is public below.
Is Codex plays NetHack production-ready?
Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Codex plays NetHack (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Reliability; its weakest is Discoverability. The per-frame breakdown is public on the Legit.Show listing; the single overall production-readiness score is reserved for the verified maker.
The 7 Frames
- Performance — 52/100
- Accessibility — 84/100
- Security — 65/100
- Privacy — 70/100
- Reliability — 100/100
- Standards — 89/100
- Discoverability — 15/100
What we measured
- Security headers present: HSTS, X-Frame-Options, X-Content-Type-Options, Referrer-Policy.
- No Content-Security-Policy.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 954 ms to first byte.
- Returns a proper 404 for unknown routes.
- 3 of 3 sampled routes reachable.
- Has a reachable privacy policy.
- Sets cookies / loads scripts with no consent prompt.
Who it's for
AI researchers · Game developers · Terminal enthusiasts · AI experimentation