Geekbench ML Score

2036
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 20 2023 04:30 PM
Views 1

System Information

System Information
Operating System Android 13
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 11.15 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 493
52.8 IPS
 
Image Classification (F16)
100% 5945
636.9 IPS
 
Image Classification (I8)
79% 9288
995.2 IPS
 
Image Segmentation (F32)
100% 622
3.84 IPS
 
Image Segmentation (F16)
96% 8415
52.0 IPS
 
Image Segmentation (I8)
89% 27075
167.2 IPS
 
Pose Estimation (F32)
100% 460
1.86 IPS
 
Pose Estimation (F16)
100% 3928
15.9 IPS
 
Pose Estimation (I8)
80% 8596
34.8 IPS
 
Object Detection (F32)
100% 425
14.9 IPS
 
Object Detection (F16)
100% 1527
53.6 IPS
 
Object Detection (I8)
50% 1752
61.5 IPS
 
Face Detection (F32)
100% 765
8.79 IPS
 
Face Detection (F16)
98% 9666
111.1 IPS
 
Face Detection (I8)
75% 20888
240.0 IPS
 
Text Classification (F32)
100% 119
47.1 IPS
 
Text Classification (F16)
100% 1295
512.1 IPS
 
Machine Translation (F32)
100% 678
104.5 IPS
 
Machine Translation (F16)
100% 674
103.9 IPS
 

Compare

Set Baseline Geekbench 6 now available