Geekbench ML Score

1914
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 17 2023 10:26 AM
Views 3

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 11.17 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 479
51.3 IPS
 
Image Classification (F16)
100% 7826
838.5 IPS
 
Image Classification (I8)
79% 11319
1.21 KIPS
 
Image Segmentation (F32)
100% 590
3.65 IPS
 
Image Segmentation (F16)
100% 10907
67.4 IPS
 
Image Segmentation (I8)
89% 34876
215.4 IPS
 
Pose Estimation (F32)
100% 452
1.83 IPS
 
Pose Estimation (F16)
100% 5723
23.2 IPS
 
Pose Estimation (I8)
80% 12489
50.5 IPS
 
Object Detection (F32)
100% 417
14.6 IPS
 
Object Detection (F16)
100% 1615
56.7 IPS
 
Object Detection (I8)
50% 1842
64.7 IPS
 
Face Detection (F32)
100% 761
8.74 IPS
 
Face Detection (F16)
100% 545
6.26 IPS
 
Face Detection (I8)
75% 27005
310.3 IPS
 
Text Classification (F32)
100% 104
41.2 IPS
 
Text Classification (F16)
100% 1071
423.6 IPS
 
Machine Translation (F32)
100% 693
106.8 IPS
 
Machine Translation (F16)
100% 696
107.3 IPS
 

Compare

Set Baseline Geekbench 6 now available