Geekbench AI Score

213
Single Precision Score
213
Half Precision Score
8207
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date October 20 2024 05:23 PM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device ARM SM7325
System Information
Operating System Android 12
Model HUAWEI BAL-AL60
Model IDHUAWEI BAL-AL60
Motherboard BAL
CPU Information
Name ARM SM7325
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.40 GHz
Memory Information
Size 7.18 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 126
23.4 IPS
 
Image Classification (HP)
100% 127
23.6 IPS
 
Image Classification (Q)
99% 7310
1.36 KIPS
 
Image Segmentation (SP)
100% 168
2.73 IPS
 
Image Segmentation (HP)
100% 170
2.75 IPS
 
Image Segmentation (Q)
98% 6763
110.0 IPS
 
Pose Estimation (SP)
100% 228
0.27 IPS
 
Pose Estimation (HP)
100% 226
0.26 IPS
 
Pose Estimation (Q)
94% 44784
52.5 IPS
 
Object Detection (SP)
100% 125
9.92 IPS
 
Object Detection (HP)
100% 126
9.96 IPS
 
Object Detection (Q)
88% 3439
275.5 IPS
 
Face Detection (SP)
100% 318
3.77 IPS
 
Face Detection (HP)
100% 320
3.80 IPS
 
Face Detection (Q)
97% 20466
244.0 IPS
 
Depth Estimation (SP)
100% 278
2.14 IPS
 
Depth Estimation (HP)
99% 280
2.16 IPS
 
Depth Estimation (Q)
64% 20416
188.0 IPS
 
Style Transfer (SP)
100% 480
0.62 IPS
 
Style Transfer (HP)
100% 469
0.60 IPS
 
Style Transfer (Q)
98% 80276
103.5 IPS
 
Image Super-Resolution (SP)
100% 133
4.93 IPS
 
Image Super-Resolution (HP)
100% 134
4.95 IPS
 
Image Super-Resolution (Q)
97% 20264
750.9 IPS
 
Text Classification (SP)
100% 189
251.7 IPS
 
Text Classification (HP)
100% 189
252.3 IPS
 
Text Classification (Q)
94% 2654
3.56 KIPS
 
Machine Translation (SP)
100% 307
5.29 IPS
 
Machine Translation (HP)
100% 307
5.29 IPS
 
Machine Translation (Q)
37% 101
10.2 IPS
 

Compare

Set Baseline Geekbench 6 now available