Geekbench ML Score

1858
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 02 2023 09:10 PM
Views 3

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 11.19 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 483
51.8 IPS
 
Image Classification (F16)
100% 6970
746.8 IPS
 
Image Classification (I8)
79% 10448
1.12 KIPS
 
Image Segmentation (F32)
100% 571
3.53 IPS
 
Image Segmentation (F16)
100% 9615
59.4 IPS
 
Image Segmentation (I8)
89% 32892
203.2 IPS
 
Pose Estimation (F32)
100% 451
1.82 IPS
 
Pose Estimation (F16)
100% 5611
22.7 IPS
 
Pose Estimation (I8)
80% 12457
50.4 IPS
 
Object Detection (F32)
100% 413
14.5 IPS
 
Object Detection (F16)
100% 1579
55.4 IPS
 
Object Detection (I8)
50% 1743
61.2 IPS
 
Face Detection (F32)
100% 759
8.72 IPS
 
Face Detection (F16)
100% 527
6.06 IPS
 
Face Detection (I8)
75% 26380
303.1 IPS
 
Text Classification (F32)
100% 104
41.1 IPS
 
Text Classification (F16)
100% 1081
427.4 IPS
 
Machine Translation (F32)
100% 695
107.2 IPS
 
Machine Translation (F16)
100% 695
107.1 IPS
 

Compare

Set Baseline Geekbench 6 now available