Unverified50% confidenceFactExact time
The final distillation configuration outperforms the non-distilled model on all eight tasks, raising the average score from 0.4813 to 0.5488, without increasing model size at inference time.
1
Sources
50%
Confidence
Long-term
Relevance
10/26/2026
First Seen
Sources
Related Entities
Related Claims
Unverified领域微调后的7B模型在任务准确率上往往超越未经微调的70B通用模型，同时推理成本降低一个数量级72% similarUnverifiedFor the 7B model, accuracy with the solver was 75.31% versus 72.02% for direct calculation, a paired improvement of +3.29 percentage points, with a 95% cluster interval of [-3.49, 10.38] crossing zero, making the advantage non-significant.71% similarUnverifiedModels' standard accuracy on the passage-level ranking task was only 0% to 13%.70% similarUnverifiedProblem quality control requires the model to have an accuracy above 80% at n=10, temperature=0.8, and without chain-of-thought, and the intermediate quantities must never appear in the prompt.69% similarUnverifiedAmong the 12 model × task combinations, only gpt-5.4-mini showed a statistically significant accuracy improvement on the logical reasoning task: jumping from 15% to 97.5%, with p=0.00056 after Holm correction.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1098462API
curl https://kongchang.com/api/v1/knowledge/claims/1098462MCP
get_claim(id=1098462)