Unverified50% confidenceFactExact time
2012年Alex Krizhevsky等人使用AlexNet在ImageNet竞赛中将top-5错误率从26%降低到15.3%，该突破基于两块GTX 580显卡的CUDA加速训练实现
1
Sources
50%
Confidence
Long-term
Relevance
8/26/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIn 2012, AlexNet won the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) by a margin of nearly 11 percentage points over the second-place entry, reducing the Top-5 error rate from 26% to 15.3%76% similarVerifiedResNet won the ImageNet competition with a top-5 error rate of 3.57%, surpassing human-level performance (approximately 5.1%) for the first time.62% similarUnverifiedCompared to FP16 original precision, FP8 quantization typically causes no more than 1–2% performance degradation on mainstream benchmarks.60% similarUnverifiedPace AI achieved 94% accuracy on an insurance Q&A benchmark using Sonnet 4.6.58% similarUnverifiedDevelopers ultimately selected the variant with the lowest KL divergence (0.028), resulting in a 1.83% drop on GSM8K, no change on MMLU, and an improvement in HarmBench compliance rate from 30.8% to 100%57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/805175API
curl https://kongchang.com/api/v1/knowledge/claims/805175MCP
get_claim(id=805175)