Geekbench ML Score

653
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 27 2025 03:49 PM
Views 3

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% 442
47.3 IPS
 
Image Classification (F16)
100% 702
75.2 IPS
 
Image Classification (I8)
80% 669
71.6 IPS
 
Image Segmentation (F32)
100% 913
5.64 IPS
 
Image Segmentation (F16)
100% 1520
9.39 IPS
 
Image Segmentation (I8)
89% 1570
9.70 IPS
 
Pose Estimation (F32)
100% 436
1.77 IPS
 
Pose Estimation (F16)
100% 781
3.16 IPS
 
Pose Estimation (I8)
80% 782
3.16 IPS
 
Object Detection (F32)
100% 372
13.1 IPS
 
Object Detection (F16)
99% 471
16.5 IPS
 
Object Detection (I8)
53% 481
16.9 IPS
 
Face Detection (F32)
100% 800
9.19 IPS
 
Face Detection (F16)
97% 1412
16.2 IPS
 
Face Detection (I8)
75% 1295
14.9 IPS
 
Text Classification (F32)
100% 428
169.5 IPS
 
Text Classification (F16)
98% 551
218.1 IPS
 
Machine Translation (F32)
100% 295
45.5 IPS
 
Machine Translation (F16)
100% 299
46.2 IPS
 

Compare

Set Baseline Geekbench 6 now available