Unverified50% confidenceFactExact time
The benchmark uses expected labels, strict label parsing, and case-level correctness judgments, with the score reflecting the proportion of cases for which the model produces the expected label.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedBenchmark data cited by vendors or platform providers are typically best-case results obtained under controlled conditions, and enterprises need to conduct independent evaluations based on their own scenarios68% similarUnverifiedMerchants should audit their product feeds to ensure that structured data fields are complete, enabling AI to parse products for comparison and decision-making.64% similarUnverifiedEvaluating label quality should weight errors by document importance rather than looking only at overall accuracy, because the cost of miscategorizing a contract is different from the cost of miscategorizing a meme.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1003399API
curl https://kongchang.com/api/v1/knowledge/claims/1003399MCP
get_claim(id=1003399)