Unverified50% confidenceFactExact time
B7 ranks first on ImageNet, whereas in this OCT four-class task B7 shows only a secondary accuracy rebound and does not surpass B1.
1
Sources
50%
Confidence
Long-term
Relevance
11/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe V1 approach achieved a self-tested top-1 accuracy of 93%, but scored 0/137 top-5 accuracy on a benchmark set of 137 real photographs.65% similarVerifiedIn 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%62% similarUnverifiedThe int4 build from Google's QAT checkpoint on Gemma 4 E2B is less than 0.5 points lower in accuracy than bf16 (0.678 vs 0.683), while the int8 build rounded directly from bf16 dropped 1.3 points.61% similarUnverifiedFP32 can only maintain approximately 7 significant digits of precision.60% similarUnverifiedOn the 78 tasks of the MMEB-V2 benchmark, PILOT outperforms the main baselines at both the 2B and 7B parameter scales.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1137862API
curl https://kongchang.com/api/v1/knowledge/claims/1137862MCP
get_claim(id=1137862)