Microsoft
Release: 2026-10-12
Tested on: 2026-10-12 12:34
microsoft/microsoft-decision-1::none
~9BDenseClosedEstimated Summary
Microsoft-Decision-1 scores 1.4 on AI BENCHY and ranks #408. It has 10.0 reliability, a 7.3% pass rate, $0.002 total cost, and 982ms average response time.
What makes Microsoft-Decision-1 unique: It stands out most in Anti-AI Tricks, where it ranks #1, while Data parsing and extraction is its weakest area at #7.
Model facts
Researched on 2026-10-12
- Parameters
- ~9B
- Architecture
- Dense
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. Microsoft identifies Qwen3.5-9B as the post-training backbone. Exact checkpoint parameter counts are not separately disclosed, so the 9B dense estimate follows that backbone. Available through Microsoft Foundry and OpenRouter; no official downloadable exact checkpoint and license were found. Returns bounded decisions without free-form text or written rationale. The OpenRouter Azure route declares no reasoning effort controls.
1.4
Consistency
4.9
10.0
$0.002
Total Output Tokens
69
Total Input Tokens
41,466
Input Price
$0.042 / 1M
Output Price
$0.000 / 1M
Cache Read Price
N/A
Cache Write Price
N/A
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Wrong Tests: 11
Attempt pass rate: 7.3%
Benchmark coverage: 36/69 attempts. Choices supplied by adapters. Supports 12/23 tests. Other tests are unsupported, not failed. Score uses the full suite.
Flaky tests
1
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Charts
Choose the first model, then click a second model to open a side-by-side page.
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Microsoft-Decision-1defaultvsSolar Decide FlashdefaultMicrosoft-Decision-1defaultvsSolar DecidedefaultMicrosoft-Decision-1defaultvsGemini 3 Flash PreviewhighMicrosoft-Decision-1defaultvsTev1 4B ExperimentaldefaultMicrosoft-Decision-1defaultvsD1defaultMicrosoft-Decision-1defaultvsClef OmnidefaultMicrosoft-Decision-1defaultvsKev 4BdefaultMicrosoft-Decision-1defaultvsGPT-6 Luna DecisionsdefaultMicrosoft-Decision-1defaultvsDrex v1.5defaultMicrosoft-Decision-1defaultvsDecider V1.1 27Bdefault
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 0.0 | 0.0 | |
| Anti-AI Tricks | 4.4 | 5.4 | |
| Coding | 2.2 | 6.7 | |
| Combined | 0.0 | 0.0 | |
| Data parsing and extraction | 3.0 | 10.0 | |
| Domain specific | 3.0 | 10.0 | |
| General Intelligence | 0.0 | 0.0 | |
| Instructions following | 1.5 | 5.0 | |
| Puzzle Solving | 1.7 | 3.3 | |
| Tool Calling | 0.0 | 0.0 | |
| Trivia | 0.0 | 0.0 |