Geekbench ML Score

347
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 11 2025 01:36 AM
Views 10

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 3.51 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 370
39.7 IPS
 
Image Classification (F16)
100% 521
55.9 IPS
 
Image Classification (I8)
80% 213
22.8 IPS
 
Image Segmentation (F32)
100% 385
2.38 IPS
 
Image Segmentation (F16)
100% 343
2.12 IPS
 
Image Segmentation (I8)
89% 858
5.30 IPS
 
Pose Estimation (F32)
100% 375
1.52 IPS
 
Pose Estimation (F16)
100% 714
2.89 IPS
 
Pose Estimation (I8)
80% 244
0.99 IPS
 
Object Detection (F32)
100% 369
13.0 IPS
 
Object Detection (F16)
100% 397
13.9 IPS
 
Object Detection (I8)
53% 168
5.89 IPS
 
Face Detection (F32)
100% 657
7.54 IPS
 
Face Detection (F16)
97% 860
9.87 IPS
 
Face Detection (I8)
75% 398
4.58 IPS
 
Text Classification (F32)
100% 190
75.1 IPS
 
Text Classification (F16)
100% 172
68.2 IPS
 
Machine Translation (F32)
100% 197
30.4 IPS
 
Machine Translation (F16)
100% 180
27.7 IPS
 

Compare

Set Baseline Geekbench 6 now available