Geekbench ML Score

409
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for Android AArch64

Result Information

Upload Date July 17 2025 12:31 AM
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 GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 211
22.6 IPS
 
Image Classification (F16)
100% 238
25.5 IPS
 
Image Classification (I8)
80% 273
29.2 IPS
 
Image Segmentation (F32)
100% 535
3.30 IPS
 
Image Segmentation (F16)
100% 986
6.09 IPS
 
Image Segmentation (I8)
89% 963
5.95 IPS
 
Pose Estimation (F32)
100% 240
0.97 IPS
 
Pose Estimation (F16)
100% 486
1.97 IPS
 
Pose Estimation (I8)
80% 507
2.05 IPS
 
Object Detection (F32)
100% 243
8.54 IPS
 
Object Detection (F16)
100% 387
13.6 IPS
 
Object Detection (I8)
54% 439
15.4 IPS
 
Face Detection (F32)
100% 562
6.46 IPS
 
Face Detection (F16)
97% 1053
12.1 IPS
 
Face Detection (I8)
75% 939
10.8 IPS
 
Text Classification (F32)
100% 261
103.1 IPS
 
Text Classification (F16)
98% 281
111.1 IPS
 
Machine Translation (F32)
100% 250
38.6 IPS
 
Machine Translation (F16)
100% 249
38.4 IPS
 

Compare

Set Baseline Geekbench 6 now available