Geekbench ML Score

1828
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date March 20 2023 10:08 AM
Views 2

System Information

System Information
Operating System Android 13
Model Google Pixel 6 Pro
Model IDGoogle Pixel 6 Pro
Motherboard raven
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 @ 2.25 GHz
Cluster 32 Cores @ 2.80 GHz
Memory Information
Size 11.25 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 687
73.6 IPS
 
Image Classification (F16)
100% 5676
608.2 IPS
 
Image Classification (I8)
79% 9386
1.01 KIPS
 
Image Segmentation (F32)
100% 1040
6.43 IPS
 
Image Segmentation (F16)
100% 7162
44.2 IPS
 
Image Segmentation (I8)
89% 29000
179.1 IPS
 
Pose Estimation (F32)
100% 841
3.40 IPS
 
Pose Estimation (F16)
80% 5413
21.9 IPS
 
Pose Estimation (I8)
80% 13346
54.0 IPS
 
Object Detection (F32)
100% 636
22.3 IPS
 
Object Detection (F16)
100% 122
4.27 IPS
 
Object Detection (I8)
50% 1853
65.0 IPS
 
Face Detection (F32)
100% 1659
19.1 IPS
 
Face Detection (F16)
100% 528
6.06 IPS
 
Face Detection (I8)
75% 17343
199.3 IPS
 
Text Classification (F32)
100% 179
70.9 IPS
 
Text Classification (F16)
100% 1118
442.1 IPS
 
Machine Translation (F32)
100% 675
104.0 IPS
 
Machine Translation (F16)
100% 674
103.9 IPS
 

Compare

Set Baseline Geekbench 6 now available