Geekbench ML Score

2025
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.2 for Android AArch64

Result Information

Upload Date August 20 2024 02:34 PM
Views 1

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 11.20 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 272
29.1 IPS
 
Image Classification (F16)
100% 6692
717.0 IPS
 
Image Classification (I8)
79% 11060
1.19 KIPS
 
Image Segmentation (F32)
100% 524
3.24 IPS
 
Image Segmentation (F16)
100% 10600
65.5 IPS
 
Image Segmentation (I8)
89% 32802
202.6 IPS
 
Pose Estimation (F32)
100% 277
1.12 IPS
 
Pose Estimation (F16)
100% 5821
23.6 IPS
 
Pose Estimation (I8)
80% 13392
54.2 IPS
 
Object Detection (F32)
100% 90
3.16 IPS
 
Object Detection (F16)
100% 4069
142.8 IPS
 
Object Detection (I8)
50% 6416
225.2 IPS
 
Face Detection (F32)
100% 485
5.57 IPS
 
Face Detection (F16)
100% 494
5.67 IPS
 
Face Detection (I8)
75% 24564
282.2 IPS
 
Text Classification (F32)
100% 1029
406.9 IPS
 
Text Classification (F16)
100% 1249
493.9 IPS
 
Machine Translation (F32)
100% 691
106.6 IPS
 
Machine Translation (F16)
100% 683
105.3 IPS
 

Compare

Set Baseline Geekbench 6 now available