AI models just got placed on the human IQ curve
Ryan Shea just launched AI IQ, a platform that ditches dense benchmark tables to map frontier AI models directly onto the human IQ bell curve. It tracks intelligence growth over time, compares models across both IQ and EQ metrics, and charts practical intelligence costs. Why it matters: It translates obscure benchmark scores into intuitive human metrics anyone can read at a glance.
If you are tired of staring at endless benchmark spreadsheets just to figure out which AI is smartest, someone just built a much more human way to look at it.
AI meets the human bell curve
Ryan Shea has officially rolled out AI IQ, a platform that ranks frontier AI models directly on the human IQ scale.
Instead of dense tables of academic test results, AI IQ plots frontier models like GPT-5.5, Claude Opus 4.7, Gemini 3.1, Grok 4.3, DeepSeek V4, Kimi K2.6, Qwen3.6, and Muse Spark onto a standard bell curve. It also tracks how frontier intelligence evolves over time, compares models across both IQ and EQ dimensions, and charts what each unit of intelligence actually costs to run.
Why it matters
For non-technical decision makers and curious users, evaluating models through dozens of obscure benchmark acronyms is a headache. Translating capability into familiar concepts like IQ and EQ gives everyone an instant visual reference point.
Overlaying intelligence scores with actual running costs is also a smart move, helping teams weigh whether marginal gains in capability justify the price tag.
That said, we think condensing intricate reasoning systems into a single human IQ number is bound to spark methodological debate. But as a visual translation layer for the broader public, it looks like a far more accessible approach than traditional leaderboards.
Sources (1)
- x.com(opens in a new tab)Originalx.com