Inkling 2 Mini tops efficiency charts: 26B looped transformer at $25.80 per correct answer

TheZachMueller · x · 2026-11-22

p0's new benchmarks crown Inkling 2 Mini as the most efficient model tested: #1 on cost-vs-intelligence, #9 overall (78.4), #1 among open-weights, lowest cost per correct answer ($25.80), and the biggest accuracy gain from web search. The looped transformer runs its middle layers three times per token, letting a 26B model reason more without generating more tokens. Mira Murati says it runs on a laptop and its thought process remains monitorable at this scale; a variable-loop research model is also being released.

Related event: Inkling 2 Mini Tops Cost-Performance Rankings as 26B Open-Weight Model(2 posts)→

Original post →

More from Infra

Infra channel →