Unverified50% confidenceBenchmarkExact time
Verdandi was benchmarked against Microsoft Azure Content Understanding on 100 documents, with the test set including 35 FATURA2 clean invoices, 25 CORD v2 real Indonesian receipt photos, 10 Kaggle scanned invoices, and 30 synthetic documents.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
Unverified在教程案例中通义灵码生成服务列表页时扫描到33个图片结果58% similarUnverifiedThe evaluation covered nine text-based scientific benchmarks, sampling 4,531 questions and 100 matched profiles, with 4,488 items completing all five conditions in full.58% similarUnverified该评测共108项检查，分三大模块：后端API与全线65分、前端页面与真实交互25分、运行构建打包10分57% similarUnverifiedIn the experiment, four agents read the same transaction documents and each updated different fields in the same client risk record.57% similarUnverifiedThe paper conducted validation on two encoders and five SCORPION scanners56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1006054API
curl https://kongchang.com/api/v1/knowledge/claims/1006054MCP
get_claim(id=1006054)