Unverified50% confidenceBenchmarkExact time
该框架在MERLIN基准上整体准确率相较当前最先进水平提升6.9%
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedEfficientNet 从 B0 到 B7，模型参数从 5.3M 增长到 66M，Top-1 精度从 77.1% 提升到 84.3%69% similarUnverified在同一模型（Claude 4.6 Opus）下，OCR的精度（Precision）为33.9%，通用Agent为7.23%，OCR精度提升约4.7倍64% similarUnverifiedNCP-ArchPreview在数学推理基准GSM8K上取得了5.99分的提升63% similarUnverified在 GSM8K 基准上，标准思维链准确率约为 56%-63%（GPT-3 规模），PAL 可提升至 72% 以上63% similarUnverifiedNVFP4量化方案相比BF16基线实现了1.5倍的推理加速，同时在top-1准确率上保留了92%到97%的水平62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/907871API
curl https://kongchang.com/api/v1/knowledge/claims/907871MCP
get_claim(id=907871)