Geekbench ML Score

2280
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date July 08 2023 08:37 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% 469
50.3 IPS
 
Image Classification (F16)
100% 7947
851.5 IPS
 
Image Classification (I8)
79% 11196
1.20 KIPS
 
Image Segmentation (F32)
100% 580
3.58 IPS
 
Image Segmentation (F16)
96% 11567
71.4 IPS
 
Image Segmentation (I8)
89% 35726
220.7 IPS
 
Pose Estimation (F32)
100% 453
1.83 IPS
 
Pose Estimation (F16)
100% 5594
22.6 IPS
 
Pose Estimation (I8)
80% 12216
49.4 IPS
 
Object Detection (F32)
100% 402
14.1 IPS
 
Object Detection (F16)
100% 1641
57.6 IPS
 
Object Detection (I8)
50% 1791
62.9 IPS
 
Face Detection (F32)
100% 788
9.06 IPS
 
Face Detection (F16)
98% 12142
139.5 IPS
 
Face Detection (I8)
75% 27145
311.9 IPS
 
Text Classification (F32)
100% 105
41.7 IPS
 
Text Classification (F16)
100% 1359
537.4 IPS
 
Machine Translation (F32)
100% 686
105.7 IPS
 
Machine Translation (F16)
100% 680
104.9 IPS
 

Compare

Set Baseline Geekbench 6 now available