Geekbench ML Score

642
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date March 14 2025 08:34 AM
Views 6

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% 433
46.4 IPS
 
Image Classification (F16)
100% 695
74.5 IPS
 
Image Classification (I8)
80% 650
69.7 IPS
 
Image Segmentation (F32)
100% 899
5.55 IPS
 
Image Segmentation (F16)
100% 1503
9.28 IPS
 
Image Segmentation (I8)
89% 1516
9.36 IPS
 
Pose Estimation (F32)
100% 415
1.68 IPS
 
Pose Estimation (F16)
100% 758
3.07 IPS
 
Pose Estimation (I8)
80% 721
2.92 IPS
 
Object Detection (F32)
100% 323
11.4 IPS
 
Object Detection (F16)
99% 494
17.3 IPS
 
Object Detection (I8)
53% 482
16.9 IPS
 
Face Detection (F32)
100% 790
9.08 IPS
 
Face Detection (F16)
97% 1403
16.1 IPS
 
Face Detection (I8)
75% 1296
14.9 IPS
 
Text Classification (F32)
100% 442
175.0 IPS
 
Text Classification (F16)
98% 552
218.5 IPS
 
Machine Translation (F32)
100% 299
46.1 IPS
 
Machine Translation (F16)
100% 302
46.6 IPS
 

Compare

Set Baseline Geekbench 6 now available