Geekbench ML Score

630
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for Android AArch64

Result Information

Upload Date January 15 2025 08:33 AM
Views 2

System Information

System Information
Operating System Android 10
Model Samsung Galaxy Note 9
Model IDsamsung SM-N960U
Motherboard sdm845
Governorschedutil
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 6 part 2050 revision 13
Base Frequency 1.77 GHz
Cluster 14 Cores @ 1.77 GHz
Cluster 24 Cores @ 2.80 GHz
Memory Information
Size 5.45 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 396
42.4 IPS
 
Image Classification (F16)
100% 658
70.5 IPS
 
Image Classification (I8)
80% 581
62.2 IPS
 
Image Segmentation (F32)
100% 1160
7.16 IPS
 
Image Segmentation (F16)
100% 1740
10.7 IPS
 
Image Segmentation (I8)
89% 2062
12.7 IPS
 
Pose Estimation (F32)
100% 517
2.09 IPS
 
Pose Estimation (F16)
100% 942
3.81 IPS
 
Pose Estimation (I8)
80% 984
3.98 IPS
 
Object Detection (F32)
100% 358
12.5 IPS
 
Object Detection (F16)
99% 496
17.4 IPS
 
Object Detection (I8)
53% 444
15.6 IPS
 
Face Detection (F32)
100% 894
10.3 IPS
 
Face Detection (F16)
97% 1324
15.2 IPS
 
Face Detection (I8)
76% 1176
13.5 IPS
 
Text Classification (F32)
100% 331
130.9 IPS
 
Text Classification (F16)
98% 378
149.7 IPS
 
Machine Translation (F32)
100% 200
30.8 IPS
 
Machine Translation (F16)
100% 189
29.2 IPS
 

Compare

Set Baseline Geekbench 6 now available