Development
A meta-eval maps twelve benchmarks onto an implied IQ of 136
Claim
A new meta-evaluation mapping a calibrated mix of twelve existing benchmarks onto implied IQs crowned GPT-5.5 the smartest available model at 136, while both its reasoning modes solved the first task on a benchmark measuring whether models can rebuild programs from scratch.
Reported metric: IQ 136
Reporting date: (not necessarily the event date)
Sources
Attribution and reporting linked by this record; links do not imply independent verification.
- Welcome to May 13, 2026 (theinnermostloop.substack.com)
Cite or correct this record
Suggest a correction — opens a GitHub draft for you to review and submit.