Geekbench ML Score

2042
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.2 for Android AArch64

Result Information

Upload Date August 20 2024 02:33 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% 249
26.7 IPS
 
Image Classification (F16)
100% 4901
525.1 IPS
 
Image Classification (I8)
79% 7187
770.1 IPS
 
Image Segmentation (F32)
100% 432
2.67 IPS
 
Image Segmentation (F16)
100% 13471
83.2 IPS
 
Image Segmentation (I8)
89% 48849
301.7 IPS
 
Pose Estimation (F32)
100% 293
1.19 IPS
 
Pose Estimation (F16)
100% 8916
36.1 IPS
 
Pose Estimation (I8)
80% 16809
68.0 IPS
 
Object Detection (F32)
100% 103
3.61 IPS
 
Object Detection (F16)
100% 100
3.51 IPS
 
Object Detection (I8)
50% 3885
136.3 IPS
 
Face Detection (F32)
100% 456
5.24 IPS
 
Face Detection (F16)
98% 11096
127.5 IPS
 
Face Detection (I8)
75% 22479
258.3 IPS
 
Text Classification (F32)
100% 1313
519.2 IPS
 
Text Classification (F16)
100% 752
297.2 IPS
 
Machine Translation (F32)
100% 1262
194.5 IPS
 
Machine Translation (F16)
100% 1256
193.6 IPS
 

Compare

Set Baseline Geekbench 6 now available