Geekbench ML Score

402
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 19 2025 06:36 PM
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 3.51 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 354
37.9 IPS
 
Image Classification (F16)
100% 528
56.6 IPS
 
Image Classification (I8)
80% 224
24.0 IPS
 
Image Segmentation (F32)
100% 438
2.71 IPS
 
Image Segmentation (F16)
100% 464
2.87 IPS
 
Image Segmentation (I8)
89% 905
5.59 IPS
 
Pose Estimation (F32)
100% 373
1.51 IPS
 
Pose Estimation (F16)
100% 719
2.91 IPS
 
Pose Estimation (I8)
80% 525
2.12 IPS
 
Object Detection (F32)
100% 366
12.9 IPS
 
Object Detection (F16)
100% 454
15.9 IPS
 
Object Detection (I8)
53% 285
10.0 IPS
 
Face Detection (F32)
100% 689
7.92 IPS
 
Face Detection (F16)
97% 884
10.2 IPS
 
Face Detection (I8)
75% 521
5.99 IPS
 
Text Classification (F32)
100% 206
81.4 IPS
 
Text Classification (F16)
100% 201
79.4 IPS
 
Machine Translation (F32)
100% 208
32.1 IPS
 
Machine Translation (F16)
100% 223
34.4 IPS
 

Compare

Set Baseline Geekbench 6 now available