Geekbench ML Score

2311
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 27 2023 03:04 AM
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% 464
49.7 IPS
 
Image Classification (F16)
100% 7471
800.5 IPS
 
Image Classification (I8)
79% 11082
1.19 KIPS
 
Image Segmentation (F32)
100% 603
3.73 IPS
 
Image Segmentation (F16)
96% 11891
73.4 IPS
 
Image Segmentation (I8)
89% 35149
217.1 IPS
 
Pose Estimation (F32)
100% 453
1.83 IPS
 
Pose Estimation (F16)
100% 5571
22.5 IPS
 
Pose Estimation (I8)
80% 12675
51.3 IPS
 
Object Detection (F32)
100% 439
15.4 IPS
 
Object Detection (F16)
100% 1640
57.5 IPS
 
Object Detection (I8)
50% 1893
66.4 IPS
 
Face Detection (F32)
100% 751
8.63 IPS
 
Face Detection (F16)
98% 12749
146.5 IPS
 
Face Detection (I8)
75% 26626
305.9 IPS
 
Text Classification (F32)
100% 121
47.9 IPS
 
Text Classification (F16)
100% 1330
526.1 IPS
 
Machine Translation (F32)
100% 695
107.2 IPS
 
Machine Translation (F16)
100% 684
105.3 IPS
 

Compare

Set Baseline Geekbench 6 now available