Geekbench ML Score

81
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

User Beamish
Upload Date December 01 2025 02:27 PM
Views 11

System Information

System Information
Operating System Android 12
Model samsung SM-A125F
Model IDsamsung SM-A125F
Motherboard a12
CPU Information
Name ARM MT6765V/CB
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3331 revision 4
Base Frequency 2.30 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.30 GHz
Memory Information
Size 3.66 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 46
4.97 IPS
 
Image Classification (F16)
100% 45
4.84 IPS
 
Image Classification (I8)
81% 214
22.9 IPS
 
Image Segmentation (F32)
100% 115
0.71 IPS
 
Image Segmentation (F16)
100% 115
0.71 IPS
 
Image Segmentation (I8)
89% 410
2.53 IPS
 
Pose Estimation (F32)
100% 58
0.24 IPS
 
Pose Estimation (F16)
100% 57
0.23 IPS
 
Pose Estimation (I8)
80% 106
0.43 IPS
 
Object Detection (F32)
100% 81
2.84 IPS
 
Object Detection (F16)
100% 81
2.84 IPS
 
Object Detection (I8)
52% 229
8.05 IPS
 
Face Detection (F32)
100% 111
1.27 IPS
 
Face Detection (F16)
100% 112
1.29 IPS
 
Face Detection (I8)
75% 292
3.35 IPS
 
Text Classification (F32)
100% 65
25.7 IPS
 
Text Classification (F16)
100% 65
25.8 IPS
 
Machine Translation (F32)
100% 10
1.59 IPS
 
Machine Translation (F16)
100% 11
1.63 IPS
 

Compare

Set Baseline Geekbench 6 now available