Geekbench AI Score

187
Single Precision Score
284
Half Precision Score
297
Quantized Score
Geekbench AI 1.0.0 for Android AArch64

Result Information

Upload Date December 22 2024 05:40 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM Qualcomm
System Information
Operating System Android 12
Model OPPO PFUM10
Model IDOPPO PFUM10
Motherboard holi
Governorschedutil
CPU Information
Name ARM Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.21 GHz
Memory Information
Size 7.24 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 106
19.7 IPS
 
Image Classification (HP)
100% 173
32.2 IPS
 
Image Classification (Q)
97% 183
34.2 IPS
 
Image Segmentation (SP)
100% 136
2.21 IPS
 
Image Segmentation (HP)
100% 252
4.08 IPS
 
Image Segmentation (Q)
98% 226
3.68 IPS
 
Pose Estimation (SP)
100% 218
0.25 IPS
 
Pose Estimation (HP)
100% 275
0.32 IPS
 
Pose Estimation (Q)
95% 272
0.32 IPS
 
Object Detection (SP)
100% 92
7.33 IPS
 
Object Detection (HP)
100% 138
10.9 IPS
 
Object Detection (Q)
86% 147
11.8 IPS
 
Face Detection (SP)
100% 255
3.03 IPS
 
Face Detection (HP)
100% 451
5.36 IPS
 
Face Detection (Q)
97% 458
5.47 IPS
 
Depth Estimation (SP)
100% 249
1.92 IPS
 
Depth Estimation (HP)
99% 429
3.31 IPS
 
Depth Estimation (Q)
75% 412
3.33 IPS
 
Style Transfer (SP)
100% 494
0.64 IPS
 
Style Transfer (HP)
100% 1069
1.37 IPS
 
Style Transfer (Q)
98% 1061
1.37 IPS
 
Image Super-Resolution (SP)
100% 128
4.72 IPS
 
Image Super-Resolution (HP)
100% 219
8.09 IPS
 
Image Super-Resolution (Q)
97% 215
7.98 IPS
 
Text Classification (SP)
100% 163
217.3 IPS
 
Text Classification (HP)
100% 163
217.1 IPS
 
Text Classification (Q)
91% 312
419.9 IPS
 
Machine Translation (SP)
100% 279
4.80 IPS
 
Machine Translation (HP)
100% 281
4.83 IPS
 
Machine Translation (Q)
57% 244
5.96 IPS
 

Compare

Set Baseline Geekbench 6 now available