Geekbench ML Score

641
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 25 2025 04:38 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% 430
46.1 IPS
 
Image Classification (F16)
100% 709
75.9 IPS
 
Image Classification (I8)
80% 665
71.3 IPS
 
Image Segmentation (F32)
100% 913
5.64 IPS
 
Image Segmentation (F16)
100% 1479
9.14 IPS
 
Image Segmentation (I8)
89% 1566
9.67 IPS
 
Pose Estimation (F32)
100% 429
1.74 IPS
 
Pose Estimation (F16)
100% 736
2.98 IPS
 
Pose Estimation (I8)
80% 752
3.04 IPS
 
Object Detection (F32)
100% 373
13.1 IPS
 
Object Detection (F16)
99% 394
13.8 IPS
 
Object Detection (I8)
53% 494
17.3 IPS
 
Face Detection (F32)
100% 805
9.25 IPS
 
Face Detection (F16)
97% 1361
15.6 IPS
 
Face Detection (I8)
75% 1288
14.8 IPS
 
Text Classification (F32)
100% 430
169.9 IPS
 
Text Classification (F16)
98% 527
208.3 IPS
 
Machine Translation (F32)
100% 305
47.0 IPS
 
Machine Translation (F16)
100% 304
46.8 IPS
 

Compare

Set Baseline Geekbench 6 now available