Geekbench ML Score

1809
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date November 26 2023 07:09 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 11.20 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 291
31.2 IPS
 
Image Classification (F16)
100% 6823
731.0 IPS
 
Image Classification (I8)
79% 11034
1.18 KIPS
 
Image Segmentation (F32)
100% 625
3.86 IPS
 
Image Segmentation (F16)
100% 10991
67.9 IPS
 
Image Segmentation (I8)
89% 32935
203.4 IPS
 
Pose Estimation (F32)
100% 329
1.33 IPS
 
Pose Estimation (F16)
100% 5826
23.6 IPS
 
Pose Estimation (I8)
80% 13161
53.3 IPS
 
Object Detection (F32)
100% 73
2.56 IPS
 
Object Detection (F16)
100% 1600
56.2 IPS
 
Object Detection (I8)
50% 1869
65.6 IPS
 
Face Detection (F32)
100% 482
5.54 IPS
 
Face Detection (F16)
100% 493
5.67 IPS
 
Face Detection (I8)
75% 24532
281.8 IPS
 
Text Classification (F32)
100% 1035
409.4 IPS
 
Text Classification (F16)
100% 1021
403.8 IPS
 
Machine Translation (F32)
100% 685
105.5 IPS
 
Machine Translation (F16)
100% 682
105.0 IPS
 

Compare

Set Baseline Geekbench 6 now available