Geekbench ML Score

262
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 07 2025 02:57 AM
Views 3

System Information

System Information
Operating System Android 15
Model samsung SM-A146P
Model IDsamsung SM-A146P
Motherboard a14xm
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 @ 2.20 GHz
Memory Information
Size 3.46 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 356
38.2 IPS
 
Image Classification (F16)
100% 462
49.5 IPS
 
Image Classification (I8)
80% 135
14.5 IPS
 
Image Segmentation (F32)
100% 270
1.67 IPS
 
Image Segmentation (F16)
100% 249
1.54 IPS
 
Image Segmentation (I8)
89% 465
2.87 IPS
 
Pose Estimation (F32)
100% 374
1.51 IPS
 
Pose Estimation (F16)
100% 707
2.86 IPS
 
Pose Estimation (I8)
80% 224
0.91 IPS
 
Object Detection (F32)
100% 257
9.02 IPS
 
Object Detection (F16)
100% 296
10.4 IPS
 
Object Detection (I8)
53% 127
4.47 IPS
 
Face Detection (F32)
100% 617
7.09 IPS
 
Face Detection (F16)
97% 709
8.14 IPS
 
Face Detection (I8)
75% 259
2.98 IPS
 
Text Classification (F32)
100% 132
52.0 IPS
 
Text Classification (F16)
100% 99
39.3 IPS
 
Machine Translation (F32)
100% 123
19.0 IPS
 
Machine Translation (F16)
100% 127
19.6 IPS
 

Compare

Set Baseline Geekbench 6 now available