Microsoft-Decision-1 benchmark
Microsoft's decision model on Microsoft Foundry. It uses the System One request format with yes/no, choice and score questions over a text or JSON state. It needs an Azure subscription and a deployment.
As of 20 Oct 2026, decidingbench has not published results for Microsoft-Decision-1. It is in the planned lineup.
Facts
- Maker
- Microsoft
- Input
- Text only
- Weights and licence
- Proprietary
Providers each pair is benchmarked separately
- Microsoft Foundry (Azure) serverlessnot published on Microsoft's page
- OpenRouter serverless$0.042 per million input tokens (to confirm)
Results by measurement
- Accuracy
- Accuracy
- Accuracy, yes/no
- Accuracy, choice
- Accuracy, score
- Confidence you can trust
- Right when 90% sure
- Decisions taken at 0.9
- Threshold honesty at 0.9
- Calibration error
- Brier score
- Order and wording
- Answers that change when options are reordered
- Answers that change when reworded
- Drop from 2 to 20 options
- Distractions and long states
- Drop with 16k tokens of distraction
- None of these
- Picks "None of these" when nothing fits
- Picks "None of these" wrongly
- Scores on a scale
- Accuracy, score
- Score within one level
- Score error in levels
- Consistency
- Answers that change on a rerun
- Safety
- Pushed by text in the state
- Images
- Accuracy with images
- Languages
- Non-English accuracy
- Speed and cost
- Latency, median
- Latency, p90
- Throughput
- Cold start
- Cost per 1,000 decisions
First results coming