Sup AI

AI ensemble that scored #1 on Humanity's Last Exam

Product HuntProductivityLaunched Apr 7, 2026100#15 of the day

About Sup AI

Every LLM hallucinates. They just don't hallucinate the same things. Sup AI runs multiple LLMs (out of 339) in parallel, then synthesizes answers by measuring confidence on every segment. High entropy = likely hallucination, downweighted. Low entropy = likely accurate, amplified. Result: 52.15% on Humanity's Last Exam, 7.41 points ahead of any individual model. $10 starter credit. Card verified. No auto-charge.

The person behind Sup AI

Scott Mueller
Maker
AI Research Scientist
Email not found yet

Sup AI's team page →

More Productivity launches

Context Engine
One memory for your AI agents and human team members.
Oct 23, 2026 · 1 person
Plango
Use AI to defend against AI
Oct 23, 2026 · 1 person
DotMD
Review your AI agent's Markdown specs like a pull request
Oct 23, 2026 · 1 person
Dots Phone
A phone-calling plugin for OpenAI Dots
Oct 23, 2026 · 1 person
Gerty
Private ChatGPT alternative that sets itself up on your Mac
Oct 23, 2026 · 1 person
25launches
Linktree for your launches.
Oct 23, 2026 · 1 person

Made Sup AI? Ask us to remove this listing or your details.