Unverified50% confidenceFactExact time
The Copilot team used Decision-1 to measure the quality of chat and agent responses, claiming its performance is competitive with GPT-5.6 Luna at approximately 100 times the speed.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/11/2026
First Seen
Valid until: 1/9/2027
Sources
Related Entities
Related Claims
UnverifiedThe evaluation set five dimensions: time-to-launch, learning curve, output quality, flexibility, and cost-effectiveness, each worth 20 points for a total of 100 points.65% similarUnverifiedIn Microsoft's internal evaluation covering 36 benchmarks and nearly 150,000 questions, Decision-1 ranked first with an average accuracy of 83.5%, surpassing Jev 1.13.0 (82.3%), Quyet-1.0-Large (81.9%), and GPT-6 Luna Decisions (79.4%).65% similarUnverifiedIn EvoArena testing, GPT-5.5, which achieved the highest Step Level score, had an accuracy of just over 50%, while Gemini-3.1 Pro and GLM-5.1, which performed best at the Chain Level, reached only approximately 28%–29%.63% similarUnverifiedThe model gave the correct answer of 34 in a multimodal image recognition test counting pencils, at a speed of 55 tokens per second at that time.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/998003API
curl https://kongchang.com/api/v1/knowledge/claims/998003MCP
get_claim(id=998003)