AI & Agents

Referee.chat

Last updated 2026-08-15 · benchmark measured 2026-08-15 — deterministic & reproducible

Referee.chat runs multi-model AI panels to argue a goal until a referee rules it done.

Is Referee.chat production-ready?

Legit.Show scores Referee.chat 93 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Referee.chat (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Privacy; its weakest is Security. Every frame it averages is published with its evidence on the Legit.Show listing.

The 7 Frames

• Performance — 99/100
• Accessibility — 96/100
• Security — 60/100
• Privacy — 100/100
• Reliability — 100/100
• Standards — 97/100
• Discoverability — 100/100

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 — 638 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

Researchers · Decision-makers · Mathematicians · Content creators · Professionals seeking evidence-based answers

Pricing

Free tier with $1 starting credit; paid credit from $10 top-up (never expires); charged per-token usage by model; 5% infrastructure fee on BYOK after first $5; unused credit refundable

Visit Referee.chat → · Alternatives to Referee.chat → · How this was measured →