How far can reasoning models scale?
How far can reasoning models scale? — o3 used 10× the training compute of o1
Why it matters
A quantitative forecast that reasoning training will reach the frontier of total training compute within about a year, after which its growth rate will converge to around 4× per year
Source — Primary sources first; secondary reports are labelled “Press”
Officialepoch.aihttps://epoch.ai/gradient-updates/how-far-can-reasoning-models-scaleAdded in Week 35, 2026 · See that week