Geekbench ML Score

445
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 03 2023 04:31 AM
Views 1

System Information

System Information
Operating System Android 13
Model Sony XQ-BC72
Model IDSony XQ-BC72
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% 298
31.9 IPS
 
Image Classification (F16)
100% 278
29.8 IPS
 
Image Classification (I8)
81% 422
45.2 IPS
 
Image Segmentation (F32)
100% 581
3.59 IPS
 
Image Segmentation (F16)
100% 560
3.46 IPS
 
Image Segmentation (I8)
89% 771
4.76 IPS
 
Pose Estimation (F32)
100% 278
1.12 IPS
 
Pose Estimation (F16)
100% 271
1.10 IPS
 
Pose Estimation (I8)
80% 133
0.54 IPS
 
Object Detection (F32)
100% 308
10.8 IPS
 
Object Detection (F16)
100% 309
10.8 IPS
 
Object Detection (I8)
52% 474
16.7 IPS
 
Face Detection (F32)
100% 439
5.04 IPS
 
Face Detection (F16)
100% 429
4.93 IPS
 
Face Detection (I8)
75% 569
6.54 IPS
 
Text Classification (F32)
100% 932
368.6 IPS
 
Text Classification (F16)
100% 932
368.5 IPS
 
Machine Translation (F32)
100% 756
116.5 IPS
 
Machine Translation (F16)
100% 756
116.6 IPS
 

Compare

Set Baseline Geekbench 6 now available