X · by yessir
Microsoft-Decision-1 against Jev on a private eval
60% F1 against 90% F1 on 3,000 private cases.
yessir
@JanahYsr
ran microsoft-decision-1 on my private eval suite (n=3000). Microsoft-Decision-1: 60% F1 VS Jev-1.13: 90% F1 draw your own conclusions but @CompleteSkeptic is right about public benchmarks @satyanadella just put the jev in the bag please
Oct 10, 2026 · 3 likesOpen on X
yessir ran Microsoft-Decision-1 on a private eval suite of 3,000 cases. He reports 60% F1 for Microsoft-Decision-1 and 90% F1 for Jev 1.13. The suite is private, so the result cannot be checked.
Open the source
