Geekbench ML Score

1639
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 15 2022 03:41 PM
Views 2

System Information

System Information
Operating System Android 13
Model Google Pixel 6 Pro
Model IDGoogle Pixel 6 Pro
Motherboard raven
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 @ 2.25 GHz
Cluster 32 Cores @ 2.80 GHz
Memory Information
Size 11.25 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 638
68.4 IPS
 
Image Classification (F16)
100% 5184
555.5 IPS
 
Image Classification (I8)
79% 8702
932.4 IPS
 
Image Segmentation (F32)
100% 1018
6.29 IPS
 
Image Segmentation (F16)
100% 6025
37.2 IPS
 
Image Segmentation (I8)
89% 24716
152.7 IPS
 
Pose Estimation (F32)
100% 847
3.43 IPS
 
Pose Estimation (F16)
80% 4612
18.7 IPS
 
Pose Estimation (I8)
80% 11564
46.8 IPS
 
Object Detection (F32)
100% 578
20.3 IPS
 
Object Detection (F16)
100% 107
3.77 IPS
 
Object Detection (I8)
50% 1458
51.2 IPS
 
Face Detection (F32)
100% 1446
16.6 IPS
 
Face Detection (F16)
100% 526
6.04 IPS
 
Face Detection (I8)
75% 15158
174.1 IPS
 
Text Classification (F32)
100% 154
61.0 IPS
 
Text Classification (F16)
100% 1120
443.1 IPS
 
Machine Translation (F32)
100% 583
89.8 IPS
 
Machine Translation (F16)
100% 581
89.6 IPS
 

Compare

Set Baseline Geekbench 6 now available