Geekbench ML Score

640
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 16 2022 08:40 AM
Views 1

System Information

System Information
Operating System Android 12
Model OnePlus 8T
Model IDOnePlus KB2003
Motherboard kona
Governorschedutil
CPU Information
Name ARM Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3341 revision 0
Base Frequency 0 MHz
Cluster 14 Cores @ 0.00 Hz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 7.38 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 904
96.9 IPS
 
Image Classification (F16)
100% 396
42.4 IPS
 
Image Classification (I8)
80% 2846
304.9 IPS
 
Image Segmentation (F32)
100% 1088
6.72 IPS
 
Image Segmentation (F16)
100% 568
3.51 IPS
 
Image Segmentation (I8)
89% 5681
35.1 IPS
 
Pose Estimation (F32)
100% 572
2.31 IPS
 
Pose Estimation (F16)
100% 266
1.08 IPS
 
Pose Estimation (I8)
80% 3712
15.0 IPS
 
Object Detection (F32)
100% 651
22.9 IPS
 
Object Detection (F16)
100% 434
15.2 IPS
 
Object Detection (I8)
52% 1320
46.3 IPS
 
Face Detection (F32)
100% 1302
15.0 IPS
 
Face Detection (F16)
100% 547
6.29 IPS
 
Face Detection (I8)
75% 5046
58.0 IPS
 
Text Classification (F32)
54% 16
6.50 IPS
 
Text Classification (F16)
54% 16
6.37 IPS
 
Machine Translation (F32)
100% 551
84.9 IPS
 
Machine Translation (F16)
100% 553
85.2 IPS
 

Compare

Set Baseline Geekbench 6 now available