Geekbench ML Score

666
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date June 11 2021 03:27 AM
Views 1

System Information

System Information
Operating System Android 11
Model OnePlus 8T
Model IDOnePlus KB2000
Motherboard kona
Governor
CPU Information
Name ARM Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3341 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 11.22 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 668
71.5 IPS
 
Image Classification (F16)
100% 1075
115.2 IPS
 
Image Classification (I8)
80% 1365
146.2 IPS
 
Image Segmentation (F32)
100% 816
5.04 IPS
 
Image Segmentation (F16)
100% 971
5.99 IPS
 
Image Segmentation (I8)
89% 3902
24.1 IPS
 
Pose Estimation (F32)
100% 410
1.66 IPS
 
Pose Estimation (F16)
100% 1560
6.31 IPS
 
Pose Estimation (I8)
80% 5572
22.5 IPS
 
Object Detection (F32)
100% 567
19.9 IPS
 
Object Detection (F16)
100% 559
19.6 IPS
 
Object Detection (I8)
52% 939
32.9 IPS
 
Face Detection (F32)
100% 919
10.6 IPS
 
Face Detection (F16)
97% 1111
12.8 IPS
 
Face Detection (I8)
75% 4496
51.6 IPS
 
Text Classification (F32)
54% 14
5.73 IPS
 
Text Classification (F16)
54% 14
5.68 IPS
 
Machine Translation (F32)
100% 393
60.6 IPS
 
Machine Translation (F16)
100% 394
60.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download