Unverified50% confidenceBenchmarkExact time
On 63 internal production classification tasks, Decider v1.3 improves accuracy by 6.54 percentage points over the classifiers currently running online.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/13/2026
First Seen
Valid until: 2/11/2027
Sources
Related Entities
Related Claims
UnverifiedJoint adaptation raises the four-benchmark macro-average accuracy from 66.46% to 74.32%.72% similarUnverifiedState-of-the-art supervised models on the LIAR benchmark still hover around 28%–32% six-class accuracy.71% similarUnverifiedThe complete system achieved an accuracy of 77.3% across six simulator-derived report fields.69% 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%).68% similarUnverifiedGLM-5.3的智能体编程准确率随投入词元增加而提升:低投入约24.7,高投入31.5,最大投入34.768% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1164874API
curl https://kongchang.com/api/v1/knowledge/claims/1164874MCP
get_claim(id=1164874)