Geekbench ML Score

514
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date November 15 2024 12:31 PM
Views 1

System Information

System Information
Operating System Android 12
Model samsung SM-F9000
Model IDsamsung SM-F9000
Motherboard
CPU Information
Name placeholder
Topology 1 Processor, 8 Cores
Identifier ARM implementer 78 architecture 8 variant 2 part 0 revision 1
Base Frequency 0 MHz
Cluster 18 Cores @ 0.00 Hz
Memory Information
Size 7.77 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 485
52.0 IPS
 
Image Classification (F16)
100% 536
57.5 IPS
 
Image Classification (I8)
81% 263
28.2 IPS
 
Image Segmentation (F32)
100% 336
2.08 IPS
 
Image Segmentation (F16)
100% 333
2.06 IPS
 
Image Segmentation (I8)
89% 340
2.10 IPS
 
Pose Estimation (F32)
100% 456
1.85 IPS
 
Pose Estimation (F16)
100% 451
1.83 IPS
 
Pose Estimation (I8)
80% 340
1.38 IPS
 
Object Detection (F32)
100% 585
20.5 IPS
 
Object Detection (F16)
100% 621
21.8 IPS
 
Object Detection (I8)
52% 475
16.7 IPS
 
Face Detection (F32)
100% 875
10.1 IPS
 
Face Detection (F16)
100% 878
10.1 IPS
 
Face Detection (I8)
75% 500
5.75 IPS
 
Text Classification (F32)
100% 545
215.7 IPS
 
Text Classification (F16)
100% 521
205.9 IPS
 
Machine Translation (F32)
100% 979
150.8 IPS
 
Machine Translation (F16)
100% 980
151.0 IPS
 

Compare

Set Baseline Geekbench 6 now available