Unverified50% confidenceFactExact time
The study finds that across the device–edge–cloud model capability ladder, models at every tier (including the most advanced cloud models) achieve significantly lower accuracy when answering non-standard register queries.
1
Sources
50%
Confidence
Long-term
Relevance
9/17/2026
First Seen
Sources
Related Entities
Related Claims
Unverified研究表明，即使在 GSM8K 或 MATH 数据集上接近满分的模型，面对稍作变形或需要跨领域组合的问题时性能下降可达30-50个百分点64% similarUnverifiedCurrent top AI models still score far below human expert levels on CTF benchmarks, especially in challenge categories involving dynamic debugging and binary analysis.64% similarUnverifiedTop academic deepfake detectors can see their accuracy plummet from 99% to below 60% when faced with previously unseen generative models, a phenomenon known as the cross-model generalization problem.64% similarUnverified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63% similarUnverifiedThe same model may rank very differently across different evaluation platforms.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/928505API
curl https://kongchang.com/api/v1/knowledge/claims/928505MCP
get_claim(id=928505)