Unverified50% confidenceBenchmarkExact time
Pricor's published benchmark uses 29 held-out columns from two distributors: keyword/type heuristics were correct on 24/29 (82.8%), Laya zero-shot on 18/29 (62.1%), fine-tuned Laya on 22/29 (75.9%), and pure prompting of Gemma on 25/29 (86.2%).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedAmong the 100 labels in the classification task, fraud and normal each accounted for 50, the majority-class baseline is 50%, and Gemma 4 31B's 55% is statistically insufficient to prove it surpasses the baseline.67% similarUnverifiedIn a standalone test of the "view incomplete" prompt on 100 questions, the wrong-answer rate was 16% without the prompt and dropped to 5% with it.64% similarUnverified20 of the 41 complete test suites achieved a perfect score of 100%, rendering the benchmark unable to differentiate among these leading models.64% similarUnverifiedCode replay inherits errors from the extraction stage; in the cluster sufficiency test, gpt-oss-120b's pass rate actually dropped from 56% to 40%.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1065585API
curl https://kongchang.com/api/v1/knowledge/claims/1065585MCP
get_claim(id=1065585)