Florian Brand on Microsoft-Decision-1’s charts: ‘you just don’t run the models everyone cares about’
Florian Brand @xeophonX
Why it matters
Representative criticism of the launch benchmarks (38k views).
Summary
Florian Brand (@xeophon) criticises the comparison in Microsoft’s launch material: ‘okay, microsoft solved chart crimes — wdym you just don’t run the models everyone cares about????’. Other posts in the same thread (e.g. @matsonj: ‘calls it jevbench, jev not listed’) make the same point.
Metrics read 2026-10-12 via api.fxtwitter.com: 38,213 views, 585 likes.
Archived text
okay, microsoft solved chart crimes
wdym you just don’t run the models everyone cares about????
Quoting @satyanadella: Introducing Microsoft-Decision-1, our new model for fast decision-making.
It delivers top performance on structured decision tasks, outperforming both LLMs and other decision models in latency and quality.
We’re already testing it across Microsoft for everything from incident response and quality control to scientific discovery.
