Truth Check/9 October 2026

“Microsoft-Decision-1 is first on accuracy across 36 benchmarks and 35 times quicker than GPT-6 Sol”

The claim as it travelled: Microsoft, 9 Oct 2026.

Microsoft's own benchmarking, with no third-party measurement yet; the chart's footnote states that Decision-1's latency was measured through Foundry while the others are JevBench's adjusted medians, and GPT-6 Sol is not ranked on the accuracy axis.

Checked Against

commandline.microsoft.com ↗Primary

Read the Check

Microsoft launches Microsoft-Decision-1, a model that only decides: a calibrated probability for each of a fixed set of options, for routing and classification, at $0.042 per million input tokens with output free

Microsoft's own 36-benchmark comparison puts it first on accuracy and 35 times quicker than GPT-6 Sol. The chart's footnote says the two latencies were measured in different places, and GPT-6 Sol is "not ranked" on the accuracy axis of the same chart.

Every claim we have checked, in the Ledger.