Unverified50% confidenceBenchmarkExact time
Program-Agent pushed the base model and the supervised fine-tuned model to 55.71% and 56.25%, respectively.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn providing correct, domain-specific justifications, performance across different models ranged from 25.6% all the way to 76.9%.74% similarUnverified同一个基座模型在不同系统提示词下的表现差异可以高达30-50个百分点70% similarUnverifiedOn the Natural Plan benchmark without task-specific training, the diffusion model's plan repair success rate was 53.7%, while the autoregressive model's was 27.0%.68% similarUnverifiedFor comparison, the Program-of-Thought baseline achieves 72.0% overall accuracy and the tool-calling agent achieves 58.7%.67% similarUnverifiedIn the experiment where the 27B model wrote its own skills, it scored 56.3% on LiveMath.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001310API
curl https://kongchang.com/api/v1/knowledge/claims/1001310MCP
get_claim(id=1001310)