Geekbench ML Score

1877
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date November 07 2023 03:18 AM
Views 1

System Information

System Information
Operating System Android 14
Model Google Pixel 7 Pro
Model IDGoogle Pixel 7 Pro
Motherboard cheetah
Governorsched_pixel
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 22 Cores @ 2.35 GHz
Cluster 32 Cores @ 2.85 GHz
Memory Information
Size 11.19 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 472
50.6 IPS
 
Image Classification (F16)
100% 7449
798.2 IPS
 
Image Classification (I8)
79% 11181
1.20 KIPS
 
Image Segmentation (F32)
100% 574
3.55 IPS
 
Image Segmentation (F16)
100% 10811
66.8 IPS
 
Image Segmentation (I8)
89% 34679
214.2 IPS
 
Pose Estimation (F32)
100% 453
1.83 IPS
 
Pose Estimation (F16)
100% 5507
22.3 IPS
 
Pose Estimation (I8)
80% 11930
48.3 IPS
 
Object Detection (F32)
100% 412
14.5 IPS
 
Object Detection (F16)
100% 1626
57.1 IPS
 
Object Detection (I8)
50% 1834
64.4 IPS
 
Face Detection (F32)
100% 781
8.97 IPS
 
Face Detection (F16)
100% 518
5.96 IPS
 
Face Detection (I8)
75% 27548
316.5 IPS
 
Text Classification (F32)
100% 90
35.8 IPS
 
Text Classification (F16)
100% 1070
423.1 IPS
 
Machine Translation (F32)
100% 692
106.7 IPS
 
Machine Translation (F16)
100% 690
106.3 IPS
 

Compare

Set Baseline Geekbench 6 now available