Unverified50% confidenceBenchmarkExact time
After fine-tuning on the Typed Decisions dataset, Layla scores 0.766, but the untuned base model scores only around 0.35, which is lower than the baseline of 0.461 obtained by always guessing the majority option.
1
Sources
50%
Confidence
Long-term
Relevance
10/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLayla's output primitives fall into three types: Choice (single-select, outputs the selected item and distribution probability), Score (rating question, gives the expected grade), and Bool (yes/no question, returns a single probability value).70% 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.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/964402API
curl https://kongchang.com/api/v1/knowledge/claims/964402MCP
get_claim(id=964402)