Show HN: I audited my AI leaderboard scale – every score dropped 6-15 points
The AGI Ranker is a transparent, reproducible leaderboard that evaluates frontier AI models across five cognitive components. After an audit, the project adjusted its scoring methodology, resulting in a 6-15 point drop for models to ensure higher accuracy and accountability.
Why it matters
As AI development accelerates, independent and transparent benchmarking is essential to distinguish genuine progress from marketing-driven performance claims.
AGI Ranker measures how close each frontier AI is to AGI. One transparent score (0-100) per model, distilled from 10 public benchmarks. Score 100 marks the AGI threshold.
Independent verification preferred over lab self-reports. Scores we can't verify are flagged, not invented. Every correction is logged publicly.
Adjust domain weights and instantly see how the AGI Score changes. Transparency at its core.
A transparent, reproducible composite index designed for maximum signal and minimum noise.
Every cell on the leaderboard cites its source. When we find a mis-attribution, an inflated self-report contradicted by independent measurement, or a stale evaluation that predates the model itself, we correct it - and log the change here.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in