Geekbench ML Score

482
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 12 2025 12:57 AM
Views 3

System Information

System Information
Operating System Android 15
Model samsung SM-A166P
Model IDsamsung SM-A166P
Motherboard a16xm
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.40 GHz
Memory Information
Size 3.35 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 309
33.1 IPS
 
Image Classification (F16)
100% 556
59.6 IPS
 
Image Classification (I8)
80% 525
56.2 IPS
 
Image Segmentation (F32)
100% 615
3.80 IPS
 
Image Segmentation (F16)
100% 1168
7.21 IPS
 
Image Segmentation (I8)
89% 1183
7.30 IPS
 
Pose Estimation (F32)
100% 229
0.93 IPS
 
Pose Estimation (F16)
100% 542
2.19 IPS
 
Pose Estimation (I8)
80% 528
2.14 IPS
 
Object Detection (F32)
100% 280
9.84 IPS
 
Object Detection (F16)
100% 442
15.5 IPS
 
Object Detection (I8)
54% 430
15.1 IPS
 
Face Detection (F32)
100% 628
7.21 IPS
 
Face Detection (F16)
97% 1162
13.3 IPS
 
Face Detection (I8)
75% 1091
12.5 IPS
 
Text Classification (F32)
100% 215
84.9 IPS
 
Text Classification (F16)
98% 460
181.8 IPS
 
Machine Translation (F32)
100% 214
33.0 IPS
 
Machine Translation (F16)
100% 211
32.5 IPS
 

Compare

Set Baseline Geekbench 6 now available