Geekbench ML Score

142
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.2 for Android AArch64

Result Information

Upload Date July 16 2025 03:35 PM
Views 1

System Information

System Information
Operating System Android 11
Model OPPO PEMM00
Model IDOPPO PEMM00
Motherboard oppo6833
CPU Information
Name ARM MT6833V/ZA
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 7.50 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 45
4.87 IPS
 
Image Classification (F16)
100% 40
4.29 IPS
 
Image Classification (I8)
81% 181
19.4 IPS
 
Image Segmentation (F32)
100% 216
1.33 IPS
 
Image Segmentation (F16)
100% 182
1.13 IPS
 
Image Segmentation (I8)
89% 329
2.03 IPS
 
Pose Estimation (F32)
100% 107
0.43 IPS
 
Pose Estimation (F16)
100% 109
0.44 IPS
 
Pose Estimation (I8)
80% 57
0.23 IPS
 
Object Detection (F32)
100% 51
1.81 IPS
 
Object Detection (F16)
100% 52
1.84 IPS
 
Object Detection (I8)
52% 259
9.09 IPS
 
Face Detection (F32)
100% 123
1.41 IPS
 
Face Detection (F16)
100% 110
1.26 IPS
 
Face Detection (I8)
75% 251
2.88 IPS
 
Text Classification (F32)
100% 450
177.8 IPS
 
Text Classification (F16)
100% 449
177.5 IPS
 
Machine Translation (F32)
100% 252
38.9 IPS
 
Machine Translation (F16)
100% 253
39.1 IPS
 

Compare

Set Baseline Geekbench 6 now available