Microsoft Decision-1 and Jev compared on a shopping agent's decisions
In a shopping agent making 20 decisions in a row, Jev placed the order in 14.5 seconds with free output, while GPT-6 Sol was still stuck at step 8 when the clip ended.
Microsoft just embarrassed OpenAI's GPT-6 Sol with a model that can't even write a sentence "Same shopping agent, same 20 decisions in a row, real time with no speedups" Every fork = 1 model call Results: Microsoft Decision-1: ordered in 13.0s for $0.042 per million tokens TypeSafe Jev: ordered in 14.5s at the exact same price, output free OpenAI GPT-6 Sol: stuck on step 8 when the clip ends, needs ~68s and charges $2 in / $10 out per million Satya Nadella's team says Decision-1 is 35x faster than GPT-6 Sol and 200x cheaper on Xbox's 10,000-review test
This post quotes another post: x.com/leopardracer/status/2108479372675977496