Geekbench ML Score

455
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date June 10 2023 08:30 AM
Views 1

System Information

System Information
Operating System Android 13
Model Sony XQ-BC42
Model IDSony XQ-BC42
Motherboard lahaina
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3396 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 10.91 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 311
33.3 IPS
 
Image Classification (F16)
100% 309
33.1 IPS
 
Image Classification (I8)
81% 420
45.0 IPS
 
Image Segmentation (F32)
100% 575
3.55 IPS
 
Image Segmentation (F16)
100% 546
3.37 IPS
 
Image Segmentation (I8)
89% 769
4.75 IPS
 
Pose Estimation (F32)
100% 270
1.09 IPS
 
Pose Estimation (F16)
100% 263
1.07 IPS
 
Pose Estimation (I8)
80% 132
0.53 IPS
 
Object Detection (F32)
100% 357
12.5 IPS
 
Object Detection (F16)
100% 351
12.3 IPS
 
Object Detection (I8)
52% 470
16.5 IPS
 
Face Detection (F32)
100% 472
5.42 IPS
 
Face Detection (F16)
100% 466
5.35 IPS
 
Face Detection (I8)
75% 565
6.49 IPS
 
Text Classification (F32)
100% 933
369.0 IPS
 
Text Classification (F16)
100% 933
369.0 IPS
 
Machine Translation (F32)
100% 744
114.6 IPS
 
Machine Translation (F16)
100% 740
114.0 IPS
 

Compare

Set Baseline Geekbench 6 now available