Geekbench AI Score

196
Single Precision Score
197
Half Precision Score
6233
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 18 2024 12:00 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device ARM ARMv8
System Information
Operating System Android 14
Model SHARP SH-M26
Model IDSHARP SH-M26
Motherboard Quess
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 2
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.21 GHz
Memory Information
Size 5.33 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 114
21.2 IPS
 
Image Classification (HP)
100% 115
21.3 IPS
 
Image Classification (Q)
97% 7028
1.31 KIPS
 
Image Segmentation (SP)
100% 155
2.52 IPS
 
Image Segmentation (HP)
100% 156
2.52 IPS
 
Image Segmentation (Q)
98% 6180
100.5 IPS
 
Pose Estimation (SP)
100% 205
0.24 IPS
 
Pose Estimation (HP)
100% 209
0.24 IPS
 
Pose Estimation (Q)
98% 21066
24.7 IPS
 
Object Detection (SP)
100% 114
9.05 IPS
 
Object Detection (HP)
100% 115
9.09 IPS
 
Object Detection (Q)
86% 3468
278.8 IPS
 
Face Detection (SP)
100% 294
3.49 IPS
 
Face Detection (HP)
100% 297
3.52 IPS
 
Face Detection (Q)
97% 20894
249.2 IPS
 
Depth Estimation (SP)
100% 252
1.94 IPS
 
Depth Estimation (HP)
99% 256
1.97 IPS
 
Depth Estimation (Q)
63% 16386
153.4 IPS
 
Style Transfer (SP)
100% 441
0.57 IPS
 
Style Transfer (HP)
100% 440
0.57 IPS
 
Style Transfer (Q)
98% 44252
57.1 IPS
 
Image Super-Resolution (SP)
100% 127
4.68 IPS
 
Image Super-Resolution (HP)
100% 126
4.66 IPS
 
Image Super-Resolution (Q)
97% 11023
408.5 IPS
 
Text Classification (SP)
100% 174
231.6 IPS
 
Text Classification (HP)
100% 174
231.9 IPS
 
Text Classification (Q)
93% 2652
3.56 KIPS
 
Machine Translation (SP)
100% 283
4.87 IPS
 
Machine Translation (HP)
100% 282
4.85 IPS
 
Machine Translation (Q)
30% 63
12.6 IPS
 

Compare

Set Baseline Geekbench 6 now available