Geekbench ML Score

2184
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 23 2022 04:01 AM
Views 3

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% 466
50.0 IPS
 
Image Classification (F16)
100% 6817
730.4 IPS
 
Image Classification (I8)
79% 10587
1.13 KIPS
 
Image Segmentation (F32)
100% 586
3.62 IPS
 
Image Segmentation (F16)
96% 11350
70.1 IPS
 
Image Segmentation (I8)
89% 33331
205.9 IPS
 
Pose Estimation (F32)
100% 453
1.83 IPS
 
Pose Estimation (F16)
100% 5760
23.3 IPS
 
Pose Estimation (I8)
80% 13442
54.4 IPS
 
Object Detection (F32)
100% 407
14.3 IPS
 
Object Detection (F16)
100% 1601
56.2 IPS
 
Object Detection (I8)
50% 1870
65.6 IPS
 
Face Detection (F32)
100% 782
8.99 IPS
 
Face Detection (F16)
98% 11594
133.2 IPS
 
Face Detection (I8)
75% 24331
279.5 IPS
 
Text Classification (F32)
100% 70
27.6 IPS
 
Text Classification (F16)
100% 1227
485.4 IPS
 
Machine Translation (F32)
100% 682
105.2 IPS
 
Machine Translation (F16)
100% 680
104.8 IPS
 

Compare

Set Baseline Geekbench 6 now available