Geekbench AI Score

194
Single Precision Score
194
Half Precision Score
574
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date January 07 2025 04:21 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device ARM Qualcomm
System Information
Operating System Android 14
Model OPPO CPH2505
Model IDOPPO CPH2505
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 7.21 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 112
20.9 IPS
 
Image Classification (HP)
100% 113
20.9 IPS
 
Image Classification (Q)
96% 594
111.0 IPS
 
Image Segmentation (SP)
100% 153
2.48 IPS
 
Image Segmentation (HP)
100% 154
2.50 IPS
 
Image Segmentation (Q)
98% 821
13.4 IPS
 
Pose Estimation (SP)
100% 208
0.24 IPS
 
Pose Estimation (HP)
100% 207
0.24 IPS
 
Pose Estimation (Q)
96% 5067
5.94 IPS
 
Object Detection (SP)
100% 112
8.92 IPS
 
Object Detection (HP)
100% 113
8.94 IPS
 
Object Detection (Q)
84% 685
55.3 IPS
 
Face Detection (SP)
100% 295
3.50 IPS
 
Face Detection (HP)
100% 296
3.52 IPS
 
Face Detection (Q)
97% 1351
16.1 IPS
 
Depth Estimation (SP)
100% 252
1.94 IPS
 
Depth Estimation (HP)
99% 253
1.95 IPS
 
Depth Estimation (Q)
64% 2896
26.6 IPS
 
Style Transfer (SP)
100% 437
0.56 IPS
 
Style Transfer (HP)
100% 437
0.56 IPS
 
Style Transfer (Q)
98% 8243
10.6 IPS
 
Image Super-Resolution (SP)
100% 125
4.61 IPS
 
Image Super-Resolution (HP)
100% 125
4.60 IPS
 
Image Super-Resolution (Q)
97% 430
15.9 IPS
 
Text Classification (SP)
100% 166
221.0 IPS
 
Text Classification (HP)
100% 167
222.3 IPS
 
Text Classification (Q)
93% 167
223.8 IPS
 
Machine Translation (SP)
100% 283
4.87 IPS
 
Machine Translation (HP)
100% 284
4.89 IPS
 
Machine Translation (Q)
0% 0
1.40 IPS
 

Compare

Set Baseline Geekbench 6 now available