Unverified50% confidenceBenchmarkExact time
Decider v1.3 reported an average accuracy of 91.6% on 63 query classification tasks.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/13/2026
First Seen
Valid until: 2/11/2027
Sources
Related Entities
Related Claims
UnverifiedThe complete system achieved an accuracy of 77.3% across six simulator-derived report fields.77% similarUnverifiedIn the Pyrite benchmark evaluation, PyriteReasoner and PyriteFeaturizer achieved ranking accuracies of 67% and 74%, respectively.76% similarUnverifiedThe V1 approach achieved a self-tested top-1 accuracy of 93%, but scored 0/137 top-5 accuracy on a benchmark set of 137 real photographs.75% 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%).74% similarUnverifiedOn 63 internal production classification tasks, Decider v1.3 improves accuracy by 6.54 percentage points over the classifiers currently running online.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1167575API
curl https://kongchang.com/api/v1/knowledge/claims/1167575MCP
get_claim(id=1167575)