Geekbench ML Score

1854
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 13 2023 11:22 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% 488
52.3 IPS
 
Image Classification (F16)
100% 7307
783.0 IPS
 
Image Classification (I8)
79% 10917
1.17 KIPS
 
Image Segmentation (F32)
100% 577
3.57 IPS
 
Image Segmentation (F16)
100% 10576
65.3 IPS
 
Image Segmentation (I8)
89% 33715
208.3 IPS
 
Pose Estimation (F32)
100% 453
1.83 IPS
 
Pose Estimation (F16)
100% 5561
22.5 IPS
 
Pose Estimation (I8)
80% 11884
48.1 IPS
 
Object Detection (F32)
100% 399
14.0 IPS
 
Object Detection (F16)
100% 1556
54.6 IPS
 
Object Detection (I8)
50% 1769
62.1 IPS
 
Face Detection (F32)
100% 791
9.08 IPS
 
Face Detection (F16)
100% 527
6.06 IPS
 
Face Detection (I8)
75% 26840
308.4 IPS
 
Text Classification (F32)
100% 90
35.8 IPS
 
Text Classification (F16)
100% 1019
403.1 IPS
 
Machine Translation (F32)
100% 680
104.7 IPS
 
Machine Translation (F16)
100% 678
104.4 IPS
 

Compare

Set Baseline Geekbench 6 now available