Geekbench ML Score

658
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date April 19 2025 05:54 PM
Views 5

System Information

System Information
Operating System Android 15
Model samsung SM-X216B
Model IDsamsung SM-X216B
Motherboard holi
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.21 GHz
Memory Information
Size 3.32 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 440
47.1 IPS
 
Image Classification (F16)
100% 718
76.9 IPS
 
Image Classification (I8)
80% 664
71.2 IPS
 
Image Segmentation (F32)
100% 900
5.56 IPS
 
Image Segmentation (F16)
100% 1514
9.35 IPS
 
Image Segmentation (I8)
89% 1559
9.63 IPS
 
Pose Estimation (F32)
100% 430
1.74 IPS
 
Pose Estimation (F16)
100% 767
3.10 IPS
 
Pose Estimation (I8)
80% 772
3.12 IPS
 
Object Detection (F32)
100% 369
12.9 IPS
 
Object Detection (F16)
99% 497
17.4 IPS
 
Object Detection (I8)
53% 473
16.6 IPS
 
Face Detection (F32)
100% 796
9.15 IPS
 
Face Detection (F16)
97% 1441
16.6 IPS
 
Face Detection (I8)
75% 1320
15.2 IPS
 
Text Classification (F32)
100% 442
174.8 IPS
 
Text Classification (F16)
98% 574
227.0 IPS
 
Machine Translation (F32)
100% 300
46.2 IPS
 
Machine Translation (F16)
100% 312
48.0 IPS
 

Compare

Set Baseline Geekbench 6 now available