Geekbench ML Score

380
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 10 2025 09:48 PM
Views 2

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% 359
38.5 IPS
 
Image Classification (F16)
100% 538
57.7 IPS
 
Image Classification (I8)
80% 189
20.3 IPS
 
Image Segmentation (F32)
100% 440
2.72 IPS
 
Image Segmentation (F16)
100% 462
2.86 IPS
 
Image Segmentation (I8)
89% 936
5.78 IPS
 
Pose Estimation (F32)
100% 374
1.51 IPS
 
Pose Estimation (F16)
100% 716
2.90 IPS
 
Pose Estimation (I8)
80% 361
1.46 IPS
 
Object Detection (F32)
100% 356
12.5 IPS
 
Object Detection (F16)
100% 456
16.0 IPS
 
Object Detection (I8)
53% 213
7.49 IPS
 
Face Detection (F32)
100% 668
7.68 IPS
 
Face Detection (F16)
97% 880
10.1 IPS
 
Face Detection (I8)
75% 451
5.18 IPS
 
Text Classification (F32)
100% 213
84.1 IPS
 
Text Classification (F16)
100% 175
69.2 IPS
 
Machine Translation (F32)
100% 209
32.2 IPS
 
Machine Translation (F16)
100% 218
33.6 IPS
 

Compare

Set Baseline Geekbench 6 now available