AI & Agents
Foresight Models
Last updated 2026-06-30 · benchmark measured 2026-08-09 — deterministic & reproducible
AI models that return calibrated probabilities instead of confident guesses.
Is Foresight Models production-ready?
Legit.Show scores Foresight Models 72 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Foresight Models (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 — 91/100
- Accessibility — 94/100
- Security — 45/100
- Privacy — 25/100
- Reliability — 100/100
- Standards — 92/100
- Discoverability — 60/100
What we measured
- Security headers present: HSTS.
- No Content-Security-Policy.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 152 ms to first byte.
- Returns a proper 404 for unknown routes.
- 3 of 3 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
Who built it
Ben Turtel · product account @lightningrodai
Who it's for
Enterprise · Government · Startups · AI agents · Prediction market operators
Pricing
$6 per 1M output tokens; $3-$50 per 1,000 forecasts depending on model variant
Visit Foresight Models → · Alternatives to Foresight Models → · How this was measured →