Geekbench ML Score

1871
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 09 2023 09:34 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 11.17 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 470
50.4 IPS
 
Image Classification (F16)
100% 7403
793.2 IPS
 
Image Classification (I8)
79% 10906
1.17 KIPS
 
Image Segmentation (F32)
100% 588
3.63 IPS
 
Image Segmentation (F16)
100% 10497
64.8 IPS
 
Image Segmentation (I8)
89% 34323
212.0 IPS
 
Pose Estimation (F32)
100% 453
1.83 IPS
 
Pose Estimation (F16)
100% 5695
23.0 IPS
 
Pose Estimation (I8)
80% 11878
48.1 IPS
 
Object Detection (F32)
100% 418
14.7 IPS
 
Object Detection (F16)
100% 1605
56.3 IPS
 
Object Detection (I8)
50% 1852
65.0 IPS
 
Face Detection (F32)
100% 752
8.63 IPS
 
Face Detection (F16)
100% 533
6.13 IPS
 
Face Detection (I8)
75% 26547
305.0 IPS
 
Text Classification (F32)
100% 89
35.2 IPS
 
Text Classification (F16)
100% 1068
422.3 IPS
 
Machine Translation (F32)
100% 694
106.9 IPS
 
Machine Translation (F16)
100% 692
106.7 IPS
 

Compare

Set Baseline Geekbench 6 now available