Unverified50% confidenceOpinionExact time
The difference between the "9-point band" and the "7-point band" is meaningful in LLM assessment; the digits after the decimal point are not.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedVocabulary choice matters more than backbone size: 10M labels with an 8k vocabulary (8.0M total parameters, bpb 1.168) beats 50M labels with a 2k vocabulary (33.5M total parameters, bpb 1.436) — 4.2 times fewer parameters but 18.7% lower bpb.63% similarUnverifiedThe 2,103-token vocabulary is directionally wrong: at the 10M scale, the 2k vocabulary has a bpb about 19% higher than the 8k one.61% similarUnverifiedThe usable resolution of LLM assessment scores is about 0.5 points, not 0.1 points.56% similarUnverifiedOn 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.56% similarUnverifiedWhen publishing scores, use bands, never put 0.1-point gaps in headlines, and state in the documentation that "scores are accurate to ±0.5."56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1036247API
curl https://kongchang.com/api/v1/knowledge/claims/1036247MCP
get_claim(id=1036247)