Geekbench ML Score

2279
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 09 2023 04:33 PM
Views 2

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% 497
53.2 IPS
 
Image Classification (F16)
100% 7538
807.7 IPS
 
Image Classification (I8)
79% 11273
1.21 KIPS
 
Image Segmentation (F32)
100% 601
3.71 IPS
 
Image Segmentation (F16)
96% 10767
66.5 IPS
 
Image Segmentation (I8)
89% 34926
215.7 IPS
 
Pose Estimation (F32)
100% 455
1.84 IPS
 
Pose Estimation (F16)
100% 5608
22.7 IPS
 
Pose Estimation (I8)
80% 13112
53.1 IPS
 
Object Detection (F32)
100% 423
14.8 IPS
 
Object Detection (F16)
100% 1634
57.3 IPS
 
Object Detection (I8)
50% 1860
65.3 IPS
 
Face Detection (F32)
100% 773
8.88 IPS
 
Face Detection (F16)
98% 11879
136.5 IPS
 
Face Detection (I8)
75% 27056
310.8 IPS
 
Text Classification (F32)
100% 103
40.8 IPS
 
Text Classification (F16)
100% 1286
508.5 IPS
 
Machine Translation (F32)
100% 683
105.2 IPS
 
Machine Translation (F16)
100% 684
105.4 IPS
 

Compare

Set Baseline Geekbench 6 now available