Unverified50% confidenceBenchmarkExact time
Laya achieves only 0.45 accuracy on the MASSIVE dataset covering 13 languages and only 0.425 on Banking77, while JAF reports 0.87 on the same tasks.
1
Sources
50%
Confidence
Long-term
Relevance
9/25/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLaya achieves an accuracy of 0.892 on Yes/No binary true-or-false judgment tasks.66% similarUnverifiedAfter fine-tuning, Laya's accuracy on the MASSIVE dataset can be improved from 0.45 to 0.85, and on another task from 0.362 to 0.766.62% similarUnverifiedMistral Small 4 scored only 0.699 on unit conversion inputs and produced 265 errors that differed from the correct label by exactly a power of ten.62% similarUnverifiedUnsloth's 1-bit build of QWEN 3 235B claims to retain 77% accuracy, but its actual score on long tasks is only 8%.60% similarUnverifiedThe locally run Gemma 26B achieved an accuracy of only 49.2% across 453 scored predictions, while its paired always-predict-up baseline had an accuracy of 53.4%.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/950934API
curl https://kongchang.com/api/v1/knowledge/claims/950934MCP
get_claim(id=950934)