Unverified50% confidenceFactExact time
On models of 4B and below, the normal-style prompt scored highest, with the plain and florid styles both dropping about 8 points, but all confidence intervals crossed zero, so the differences cannot be strictly proven significant.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe perplexity of the florid-style prompt was about twice that of the normal style (Qwen3 0.6B: 37.2 vs 16.7), but the perplexity of the plain style and the normal style were almost the same (15.6 vs 16.7), yet the small model performed worse on the plain style.73% 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.61% similarUnverifiedOn the GSM8K mathematical reasoning test, Qwen3-4B scores 0.915 and Gemma 4 E2B scores 0.911, a difference of +0.4 percentage points with a confidence interval crossing zero, making it the only model on par with Gemma.61% similarUnverifiedThe degree-3 and degree-4 polynomial coefficients in the paper are obtained by minimizing the maximum error (minimax approximation) in the BF16/FP16 target format.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1018318API
curl https://kongchang.com/api/v1/knowledge/claims/1018318MCP
get_claim(id=1018318)