Development

A meta-eval maps twelve benchmarks onto an implied IQ of 136

development2026-05-13

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.

Knowledge graphopen in browser →

Reported in
Actor
Evidence for
Supersedes
Referenced by

Cite or correct this record

Suggest a correction — opens a GitHub draft for you to review and submit.