Geekbench ML Score

1606
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date March 01 2025 05:52 PM
Views 4

System Information

System Information
Operating System Android 15
Model Google Pixel 8
Model IDGoogle Pixel 8
Motherboard shiba
Governorsched_pixel
CPU Information
Name ARM ARMv8
Topology 1 Processor, 9 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3406 revision 0
Base Frequency 1.70 GHz
Cluster 14 Cores @ 1.70 GHz
Cluster 24 Cores @ 2.37 GHz
Cluster 31 Core @ 2.91 GHz
Memory Information
Size 7.42 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 105
11.2 IPS
 
Image Classification (F16)
100% 3324
356.1 IPS
 
Image Classification (I8)
79% 5304
568.3 IPS
 
Image Segmentation (F32)
100% 349
2.16 IPS
 
Image Segmentation (F16)
100% 12588
77.8 IPS
 
Image Segmentation (I8)
89% 33508
207.0 IPS
 
Pose Estimation (F32)
100% 228
0.92 IPS
 
Pose Estimation (F16)
100% 8582
34.7 IPS
 
Pose Estimation (I8)
80% 17279
69.9 IPS
 
Object Detection (F32)
100% 109
3.83 IPS
 
Object Detection (F16)
100% 117
4.09 IPS
 
Object Detection (I8)
50% 1763
61.9 IPS
 
Face Detection (F32)
100% 234
2.69 IPS
 
Face Detection (F16)
98% 10659
122.5 IPS
 
Face Detection (I8)
75% 19108
219.5 IPS
 
Text Classification (F32)
100% 1144
452.3 IPS
 
Text Classification (F16)
100% 793
313.5 IPS
 
Machine Translation (F32)
100% 957
147.4 IPS
 
Machine Translation (F16)
100% 955
147.1 IPS
 

Compare

Set Baseline Geekbench 6 now available