Unverified50% confidenceSolutionExact time
The self-built benchmark contains a large number of proprietary questions not included in mainstream large model training data, enabling it to reflect models' generalization ability rather than memorization ability.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMainstream benchmark problems have been widely discussed on the internet, and models' training data may contain memorization of these problems, causing benchmark scores to overestimate the models' capabilities on truly unseen tasks76% similarUnverifiedSWE-bench上已有多个研究团队记录到「patch记忆」现象，即模型通过识别问题描述特征检索训练时见过的补丁73% similarUnverifiedBenchmaxxing refers to the behavior of over-optimizing specific metrics at the expense of overall balance, manifesting in large model development as carefully designing training data ratios and adjusting loss function weights targeting known benchmarks to improve performance on specific tasks.72% similarVerifiedFrontier models exhibit emergent capabilities, meaning they suddenly display abilities not explicitly included in the training objective once a certain parameter-scale threshold is reached.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/908651API
curl https://kongchang.com/api/v1/knowledge/claims/908651MCP
get_claim(id=908651)