Microsoft-Decision-1: Release, Decision Index Score, Performance & Price
Model summary
Compared with other decision models, Microsoft-Decision-1 is above average on the Decision Index and reasonably priced. It's also slower than average. The model supports text input and has a 33k tokens context window.
Microsoft-Decision-1 scores 54 on the Artificial Analysis Decision Index, placing it above average among decision models (median: 53).
At 207 ms per task, Microsoft-Decision-1 is slower than average (median: 188 ms).
Pricing for Microsoft-Decision-1 is $0.042 per 1M input tokens. On average, it costs $31 per 1M tasks to run Microsoft-Decision-1 on the Decision Index (moderately priced, median: $32).
| Creator | Microsoft |
|---|---|
| Provider | OpenRouter |
| Input modality | Supports: text |
| Context window | 33k |
| Input price | $0.042 per 1M tokens |
Score
Artificial Analysis Decision Index
Weighted average of AA-Omniscience-Decision, HLE-MultiChoice, When2Call and WildGuardTest · Higher is better
Artificial Analysis Decision Index vs. Cost per 1M Tasks
Artificial Analysis Decision Index score vs. average cost per 1 million tasks (USD) · Lower is better
Most attractive quadrant
Pareto line
Calibration
Artificial Analysis Decision Index Calibration
Accuracy against the probability the model gave its chosen answer · Bins of 0.1 with at least 20 answers · Each benchmark weighted equally
Calibration for language models coming soon.
Time
Artificial Analysis Decision Index: Time per Task
Median time per task over every task across all Artificial Analysis Decision Index evaluations · Lower is better
Cost
Artificial Analysis Decision Index: Cost per 1M Tasks
Average cost per 1 million tasks across all Artificial Analysis Decision Index evaluations at current prices (USD) · Lower is better