AI & Agents

NetHackers

Last updated 2026-09-24 · benchmark measured 2026-09-24 — deterministic & reproducible

An open competition to build the first program that can reliably win NetHack 3.6.6.

Are you the maker of NetHackers? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.

Launched something? Add your product, free.

To cite this score: legit.show/s/nethackers-dunnolab-ai/2026-09-24. That address never changes; this page moves with every re-measure.

Legit.Show scored NetHackers 75/100 on 2026-09-24, measured across all 7 frames from its public surface. legit.show/s/nethackers-dunnolab-ai/2026-09-24

Is NetHackers production-ready?

Legit.Show scores NetHackers 75 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on NetHackers (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Reliability; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.

The 7 Frames

• Performance — 99/100
• Accessibility — 90/100
• Security — 60/100
  How this compares across the catalogue: The Web Security Baseline
• Privacy — 25/100
  How this compares across the catalogue: The Privacy Gap
• Reliability — 100/100
• Standards — 89/100
• Discoverability — 60/100

What we measured

• Security headers present: X-Frame-Options, X-Content-Type-Options, Referrer-Policy.
• No Content-Security-Policy and no HSTS.
• Served over HTTPS with a valid certificate.
• Real Lighthouse performance run — 852 ms to first byte.
• Returns a proper 404 for unknown routes.
• 1 of 1 sampled routes reachable.
• No privacy policy found.
• Sets cookies / loads scripts with no consent prompt.

Who it's for

AI researchers · Coding agent builders · NetHack enthusiasts · Recursive learning researchers · Game AI developers

Visit NetHackers → · Alternatives to NetHackers → · How this was measured →