Geekbench ML Score

2259
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 03 2023 09:34 PM
Views 2

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% 542
58.1 IPS
 
Image Classification (F16)
100% 6963
746.0 IPS
 
Image Classification (I8)
79% 10612
1.14 KIPS
 
Image Segmentation (F32)
100% 583
3.60 IPS
 
Image Segmentation (F16)
100% 10499
64.9 IPS
 
Image Segmentation (I8)
89% 34571
213.5 IPS
 
Pose Estimation (F32)
100% 447
1.81 IPS
 
Pose Estimation (F16)
100% 5660
22.9 IPS
 
Pose Estimation (I8)
80% 12618
51.1 IPS
 
Object Detection (F32)
100% 432
15.2 IPS
 
Object Detection (F16)
100% 1614
56.6 IPS
 
Object Detection (I8)
50% 1822
64.0 IPS
 
Face Detection (F32)
100% 842
9.67 IPS
 
Face Detection (F16)
98% 12866
147.8 IPS
 
Face Detection (I8)
75% 26339
302.6 IPS
 
Text Classification (F32)
100% 108
42.6 IPS
 
Text Classification (F16)
100% 1074
425.0 IPS
 
Machine Translation (F32)
100% 683
105.2 IPS
 
Machine Translation (F16)
100% 688
106.1 IPS
 

Compare

Set Baseline Geekbench 6 now available