Geekbench ML Score

604
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date March 19 2025 03:58 PM
Views 4

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% 422
45.2 IPS
 
Image Classification (F16)
100% 670
71.8 IPS
 
Image Classification (I8)
80% 625
66.9 IPS
 
Image Segmentation (F32)
100% 875
5.40 IPS
 
Image Segmentation (F16)
100% 1467
9.06 IPS
 
Image Segmentation (I8)
89% 1481
9.15 IPS
 
Pose Estimation (F32)
100% 422
1.71 IPS
 
Pose Estimation (F16)
100% 755
3.06 IPS
 
Pose Estimation (I8)
80% 757
3.06 IPS
 
Object Detection (F32)
100% 319
11.2 IPS
 
Object Detection (F16)
99% 351
12.3 IPS
 
Object Detection (I8)
53% 395
13.9 IPS
 
Face Detection (F32)
100% 768
8.83 IPS
 
Face Detection (F16)
97% 1370
15.7 IPS
 
Face Detection (I8)
75% 1254
14.4 IPS
 
Text Classification (F32)
100% 387
153.0 IPS
 
Text Classification (F16)
98% 471
186.3 IPS
 
Machine Translation (F32)
100% 286
44.1 IPS
 
Machine Translation (F16)
100% 282
43.5 IPS
 

Compare

Set Baseline Geekbench 6 now available