Geekbench ML Score

656
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date March 26 2025 01:31 PM
Views 1

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 3.29 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 421
45.1 IPS
 
Image Classification (F16)
100% 672
72.0 IPS
 
Image Classification (I8)
80% 658
70.5 IPS
 
Image Segmentation (F32)
100% 875
5.41 IPS
 
Image Segmentation (F16)
100% 1462
9.03 IPS
 
Image Segmentation (I8)
89% 1480
9.14 IPS
 
Pose Estimation (F32)
100% 434
1.76 IPS
 
Pose Estimation (F16)
100% 817
3.31 IPS
 
Pose Estimation (I8)
80% 774
3.13 IPS
 
Object Detection (F32)
100% 367
12.9 IPS
 
Object Detection (F16)
99% 494
17.3 IPS
 
Object Detection (I8)
53% 494
17.3 IPS
 
Face Detection (F32)
100% 804
9.23 IPS
 
Face Detection (F16)
97% 1428
16.4 IPS
 
Face Detection (I8)
75% 1309
15.0 IPS
 
Text Classification (F32)
100% 445
176.1 IPS
 
Text Classification (F16)
98% 529
209.4 IPS
 
Machine Translation (F32)
100% 322
49.7 IPS
 
Machine Translation (F16)
100% 338
52.0 IPS
 

Compare

Set Baseline Geekbench 6 now available