Geekbench ML Score

2287
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 23 2023 06:01 PM
Views 1

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% 498
53.4 IPS
 
Image Classification (F16)
100% 7651
819.7 IPS
 
Image Classification (I8)
79% 11141
1.19 KIPS
 
Image Segmentation (F32)
100% 594
3.67 IPS
 
Image Segmentation (F16)
96% 10939
67.6 IPS
 
Image Segmentation (I8)
89% 34611
213.8 IPS
 
Pose Estimation (F32)
100% 455
1.84 IPS
 
Pose Estimation (F16)
100% 5596
22.6 IPS
 
Pose Estimation (I8)
80% 12215
49.4 IPS
 
Object Detection (F32)
100% 451
15.8 IPS
 
Object Detection (F16)
100% 1645
57.7 IPS
 
Object Detection (I8)
50% 1849
64.9 IPS
 
Face Detection (F32)
100% 792
9.09 IPS
 
Face Detection (F16)
98% 13057
150.0 IPS
 
Face Detection (I8)
75% 27635
317.5 IPS
 
Text Classification (F32)
100% 94
37.3 IPS
 
Text Classification (F16)
100% 1299
513.6 IPS
 
Machine Translation (F32)
100% 686
105.7 IPS
 
Machine Translation (F16)
100% 688
106.0 IPS
 

Compare

Set Baseline Geekbench 6 now available