Geekbench ML Score

277
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 13 2025 06:51 AM
Views 4

System Information

System Information
Operating System Android 15
Model samsung SM-A146U
Model IDsamsung SM-A146U
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% 346
37.0 IPS
 
Image Classification (F16)
100% 485
52.0 IPS
 
Image Classification (I8)
80% 134
14.4 IPS
 
Image Segmentation (F32)
100% 281
1.73 IPS
 
Image Segmentation (F16)
100% 278
1.72 IPS
 
Image Segmentation (I8)
89% 565
3.49 IPS
 
Pose Estimation (F32)
100% 378
1.53 IPS
 
Pose Estimation (F16)
100% 704
2.85 IPS
 
Pose Estimation (I8)
80% 269
1.09 IPS
 
Object Detection (F32)
100% 248
8.70 IPS
 
Object Detection (F16)
100% 319
11.2 IPS
 
Object Detection (I8)
53% 156
5.49 IPS
 
Face Detection (F32)
100% 612
7.03 IPS
 
Face Detection (F16)
97% 697
8.00 IPS
 
Face Detection (I8)
75% 309
3.55 IPS
 
Text Classification (F32)
100% 127
50.2 IPS
 
Text Classification (F16)
100% 101
39.9 IPS
 
Machine Translation (F32)
100% 129
19.9 IPS
 
Machine Translation (F16)
100% 136
20.9 IPS
 

Compare

Set Baseline Geekbench 6 now available