Geekbench ML Score

2187
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date November 24 2022 05:18 PM
Views 2

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

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 492
52.7 IPS
 
Image Classification (F16)
100% 6833
732.1 IPS
 
Image Classification (I8)
79% 10777
1.15 KIPS
 
Image Segmentation (F32)
100% 604
3.73 IPS
 
Image Segmentation (F16)
96% 10714
66.2 IPS
 
Image Segmentation (I8)
89% 34491
213.0 IPS
 
Pose Estimation (F32)
100% 451
1.83 IPS
 
Pose Estimation (F16)
100% 5805
23.5 IPS
 
Pose Estimation (I8)
80% 13281
53.7 IPS
 
Object Detection (F32)
100% 388
13.6 IPS
 
Object Detection (F16)
100% 1612
56.6 IPS
 
Object Detection (I8)
50% 1875
65.8 IPS
 
Face Detection (F32)
100% 750
8.62 IPS
 
Face Detection (F16)
98% 11528
132.4 IPS
 
Face Detection (I8)
75% 24209
278.1 IPS
 
Text Classification (F32)
100% 67
26.7 IPS
 
Text Classification (F16)
100% 1289
509.8 IPS
 
Machine Translation (F32)
100% 695
107.1 IPS
 
Machine Translation (F16)
100% 693
106.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download