SOTA Neural Network Inference benchmarks and papers with code

Benchmarks

Dataset Name	SOTA Method	Metric
ARM Embedded Processors inference latency		Latency (ms)0.071	56	5mo ago
OnePlus 11	Fine-Grained CPU-GPU Co-Execution	Baseline Latency (ms)8.5	4	5mo ago
Moto 2022	Fine-Grained CPU-GPU Co-Execution	Baseline Latency (ms)7.5	4	5mo ago
Pixel 5	Fine-Grained CPU-GPU Co-Execution	Baseline Latency (ms)33.2	4	5mo ago
Pixel 4	Fine-Grained CPU-GPU Co-Execution	Baseline Latency (ms)17.5	4	5mo ago

Showing 5 of 5 rows