Geekbench ML Score

1918
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.2 for Android AArch64

Result Information

Upload Date August 20 2024 02:36 PM
Views 1

System Information

System Information
Operating System Android 14
Model Google Pixel 9 Pro XL
Model IDGoogle Pixel 9 Pro XL
Motherboard komodo
Governorsched_pixel
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3458 revision 1
Base Frequency 1.95 GHz
Cluster 14 Cores @ 1.95 GHz
Cluster 23 Cores @ 2.60 GHz
Cluster 31 Core @ 3.10 GHz
Memory Information
Size 15.19 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 259
27.8 IPS
 
Image Classification (F16)
100% 4694
502.9 IPS
 
Image Classification (I8)
79% 6371
682.6 IPS
 
Image Segmentation (F32)
100% 295
1.82 IPS
 
Image Segmentation (F16)
100% 13878
85.7 IPS
 
Image Segmentation (I8)
89% 40001
247.1 IPS
 
Pose Estimation (F32)
100% 288
1.17 IPS
 
Pose Estimation (F16)
100% 8862
35.9 IPS
 
Pose Estimation (I8)
80% 17893
72.4 IPS
 
Object Detection (F32)
100% 131
4.59 IPS
 
Object Detection (F16)
100% 105
3.70 IPS
 
Object Detection (I8)
50% 4383
153.8 IPS
 
Face Detection (F32)
100% 215
2.48 IPS
 
Face Detection (F16)
98% 10955
125.9 IPS
 
Face Detection (I8)
75% 21647
248.7 IPS
 
Text Classification (F32)
100% 1291
510.8 IPS
 
Text Classification (F16)
100% 659
260.8 IPS
 
Machine Translation (F32)
100% 1263
194.7 IPS
 
Machine Translation (F16)
100% 1243
191.6 IPS
 

Compare

Set Baseline Geekbench 6 now available