Geekbench ML Score

296
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.2 for Android AArch64

Result Information

Upload Date August 05 2025 07:20 AM
Views 13

System Information

System Information
Operating System Android 10
Model OPPO PAFM00
Model IDOPPO PAFM00
Motherboard sdm845
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 6 part 2050 revision 13
Base Frequency 1.77 GHz
Cluster 14 Cores @ 1.77 GHz
Cluster 24 Cores @ 2.80 GHz
Memory Information
Size 7.31 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 282
30.2 IPS
 
Image Classification (F16)
100% 308
33.0 IPS
 
Image Classification (I8)
80% 473
50.7 IPS
 
Image Segmentation (F32)
100% 270
1.67 IPS
 
Image Segmentation (F16)
100% 276
1.70 IPS
 
Image Segmentation (I8)
89% 380
2.35 IPS
 
Pose Estimation (F32)
100% 284
1.15 IPS
 
Pose Estimation (F16)
100% 673
2.73 IPS
 
Pose Estimation (I8)
80% 214
0.87 IPS
 
Object Detection (F32)
100% 510
17.9 IPS
 
Object Detection (F16)
100% 540
19.0 IPS
 
Object Detection (I8)
52% 658
23.1 IPS
 
Face Detection (F32)
100% 610
7.01 IPS
 
Face Detection (F16)
100% 699
8.03 IPS
 
Face Detection (I8)
75% 1299
14.9 IPS
 
Text Classification (F32)
100% 19
7.59 IPS
 
Text Classification (F16)
100% 19
7.46 IPS
 
Machine Translation (F32)
100% 236
36.4 IPS
 
Machine Translation (F16)
100% 235
36.3 IPS
 

Compare

Set Baseline Geekbench 6 now available