Geekbench ML Score

357
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 10 2025 11:13 PM
Views 5

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% 365
39.1 IPS
 
Image Classification (F16)
100% 534
57.2 IPS
 
Image Classification (I8)
80% 166
17.8 IPS
 
Image Segmentation (F32)
100% 409
2.53 IPS
 
Image Segmentation (F16)
100% 417
2.58 IPS
 
Image Segmentation (I8)
89% 897
5.54 IPS
 
Pose Estimation (F32)
100% 372
1.51 IPS
 
Pose Estimation (F16)
100% 711
2.88 IPS
 
Pose Estimation (I8)
80% 370
1.50 IPS
 
Object Detection (F32)
100% 337
11.8 IPS
 
Object Detection (F16)
100% 314
11.0 IPS
 
Object Detection (I8)
53% 190
6.66 IPS
 
Face Detection (F32)
100% 659
7.57 IPS
 
Face Detection (F16)
97% 789
9.06 IPS
 
Face Detection (I8)
75% 406
4.66 IPS
 
Text Classification (F32)
100% 202
79.9 IPS
 
Text Classification (F16)
100% 170
67.0 IPS
 
Machine Translation (F32)
100% 215
33.2 IPS
 
Machine Translation (F16)
100% 209
32.2 IPS
 

Compare

Set Baseline Geekbench 6 now available