Geekbench ML Score

494
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date April 25 2025 04:57 PM
Views 7

System Information

System Information
Operating System Android 15
Model samsung SM-M166P
Model IDsamsung SM-M166P
Motherboard m16xm
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 7.27 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 317
34.0 IPS
 
Image Classification (F16)
100% 552
59.1 IPS
 
Image Classification (I8)
80% 521
55.9 IPS
 
Image Segmentation (F32)
100% 647
4.00 IPS
 
Image Segmentation (F16)
100% 1229
7.59 IPS
 
Image Segmentation (I8)
89% 1236
7.63 IPS
 
Pose Estimation (F32)
100% 239
0.97 IPS
 
Pose Estimation (F16)
100% 571
2.31 IPS
 
Pose Estimation (I8)
80% 561
2.27 IPS
 
Object Detection (F32)
100% 304
10.7 IPS
 
Object Detection (F16)
100% 471
16.5 IPS
 
Object Detection (I8)
54% 454
15.9 IPS
 
Face Detection (F32)
100% 674
7.74 IPS
 
Face Detection (F16)
97% 1298
14.9 IPS
 
Face Detection (I8)
75% 1191
13.7 IPS
 
Text Classification (F32)
100% 269
106.5 IPS
 
Text Classification (F16)
98% 305
120.8 IPS
 
Machine Translation (F32)
100% 195
30.1 IPS
 
Machine Translation (F16)
100% 211
32.5 IPS
 

Compare

Set Baseline Geekbench 6 now available