Geekbench ML Score

660
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 14 2025 01:15 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 3.29 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 438
47.0 IPS
 
Image Classification (F16)
100% 710
76.0 IPS
 
Image Classification (I8)
80% 667
71.5 IPS
 
Image Segmentation (F32)
100% 911
5.63 IPS
 
Image Segmentation (F16)
100% 1521
9.40 IPS
 
Image Segmentation (I8)
89% 1561
9.64 IPS
 
Pose Estimation (F32)
100% 426
1.72 IPS
 
Pose Estimation (F16)
100% 781
3.16 IPS
 
Pose Estimation (I8)
80% 779
3.15 IPS
 
Object Detection (F32)
100% 378
13.2 IPS
 
Object Detection (F16)
99% 522
18.3 IPS
 
Object Detection (I8)
53% 488
17.1 IPS
 
Face Detection (F32)
100% 825
9.48 IPS
 
Face Detection (F16)
97% 1417
16.3 IPS
 
Face Detection (I8)
75% 1304
15.0 IPS
 
Text Classification (F32)
100% 444
175.5 IPS
 
Text Classification (F16)
98% 516
204.1 IPS
 
Machine Translation (F32)
100% 312
48.0 IPS
 
Machine Translation (F16)
100% 308
47.4 IPS
 

Compare

Set Baseline Geekbench 6 now available