Geekbench ML Score

2089
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 09 2023 03:28 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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 486
52.1 IPS
 
Image Classification (F16)
100% 6434
689.4 IPS
 
Image Classification (I8)
79% 9821
1.05 KIPS
 
Image Segmentation (F32)
100% 596
3.68 IPS
 
Image Segmentation (F16)
96% 9367
57.9 IPS
 
Image Segmentation (I8)
89% 29546
182.5 IPS
 
Pose Estimation (F32)
100% 457
1.85 IPS
 
Pose Estimation (F16)
100% 4573
18.5 IPS
 
Pose Estimation (I8)
80% 10236
41.4 IPS
 
Object Detection (F32)
100% 417
14.6 IPS
 
Object Detection (F16)
100% 1536
53.9 IPS
 
Object Detection (I8)
50% 1779
62.4 IPS
 
Face Detection (F32)
100% 823
9.45 IPS
 
Face Detection (F16)
98% 10716
123.1 IPS
 
Face Detection (I8)
75% 23029
264.6 IPS
 
Text Classification (F32)
100% 86
34.2 IPS
 
Text Classification (F16)
100% 1239
490.0 IPS
 
Machine Translation (F32)
100% 673
103.7 IPS
 
Machine Translation (F16)
100% 671
103.4 IPS
 

Compare

Set Baseline Geekbench 6 now available