Unverified50% confidenceFactExact time
Written priority rules achieve a 59/60 joint success rate in the joint task, outperforming the 38/60 of code examples.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCode-type tasks can achieve a throughput improvement of about 4x or more (154 vs 18-19 tok/s), while prose-type tasks achieve only about 2x (35-37 vs 18-19 tok/s).66% similarUnverifiedCorpus 3.6 27B在深度任务、结构化输出、编程能力上胜出，其中编程能力领先1.66分62% similarUnverifiedThe production keyword rule achieves only 28% accuracy on the message type field, while the majority-class baseline is 58%.62% similarUnverifiedIn this test, Base44 scored 100, went from prompt to launch in about 3.5 minutes (the fastest of the four), required 0 fix prompts, and consumed 1 of 25 messages on the free tier.62% similarUnverifiedIn the experiment, the 27B model scored 61.0% on LiveMath when skills were written by the 4B model, whereas it scored 56.3% when it wrote the skills itself62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1114384API
curl https://kongchang.com/api/v1/knowledge/claims/1114384MCP
get_claim(id=1114384)