Geekbench ML Score

298
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.2 for Android AArch64

Result Information

Upload Date August 03 2025 03:56 AM
Views 7

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% 280
30.1 IPS
 
Image Classification (F16)
100% 312
33.4 IPS
 
Image Classification (I8)
80% 487
52.2 IPS
 
Image Segmentation (F32)
100% 269
1.66 IPS
 
Image Segmentation (F16)
100% 272
1.68 IPS
 
Image Segmentation (I8)
89% 370
2.29 IPS
 
Pose Estimation (F32)
100% 284
1.15 IPS
 
Pose Estimation (F16)
100% 673
2.72 IPS
 
Pose Estimation (I8)
80% 218
0.88 IPS
 
Object Detection (F32)
100% 490
17.2 IPS
 
Object Detection (F16)
100% 628
22.1 IPS
 
Object Detection (I8)
52% 661
23.2 IPS
 
Face Detection (F32)
100% 600
6.90 IPS
 
Face Detection (F16)
100% 700
8.04 IPS
 
Face Detection (I8)
75% 1319
15.2 IPS
 
Text Classification (F32)
100% 19
7.33 IPS
 
Text Classification (F16)
100% 19
7.45 IPS
 
Machine Translation (F32)
100% 235
36.1 IPS
 
Machine Translation (F16)
100% 237
36.5 IPS
 

Compare

Set Baseline Geekbench 6 now available