Geekbench AI Score

493
Single Precision Score
169
Half Precision Score
173
Quantized Score
Geekbench AI 1.0.0 for Windows AArch64

Result Information

User grinceur
Upload Date August 18 2024 04:22 PM
Views 2

System Information

AI Information
Framework ONNX
Backend QNN
Device Microsoft SQ1 @ 3.0 GHz
System Information
Operating System Microsoft Windows 11 Professionnel (64-bit)
Model Microsoft Corporation Surface Pro X
Motherboard Microsoft Corporation Surface Pro X
Power PlanUtilisation normale
CPU Information
Name Microsoft SQ1 @ 3.0 GHz
Topology 1 Processor, 8 Cores
Identifier ARMv8 (64-bit) Family 8 Model 805 Revision D0E
Base Frequency 3.00 GHz
Cluster 14 Cores
Cluster 24 Cores
Memory Information
Size 8.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 206
38.3 IPS
 
Image Classification (HP)
100% 64
11.9 IPS
 
Image Classification (Q)
100% 105
19.6 IPS
 
Image Segmentation (SP)
100% 264
4.28 IPS
 
Image Segmentation (HP)
100% 97
1.57 IPS
 
Image Segmentation (Q)
98% 121
1.97 IPS
 
Pose Estimation (SP)
100% 851
0.99 IPS
 
Pose Estimation (HP)
100% 284
0.33 IPS
 
Pose Estimation (Q)
95% 248
0.29 IPS
 
Object Detection (SP)
100% 230
18.2 IPS
 
Object Detection (HP)
99% 74
5.87 IPS
 
Object Detection (Q)
89% 91
7.25 IPS
 
Face Detection (SP)
100% 627
7.45 IPS
 
Face Detection (HP)
100% 126
1.50 IPS
 
Face Detection (Q)
97% 245
2.92 IPS
 
Depth Estimation (SP)
100% 652
5.03 IPS
 
Depth Estimation (HP)
99% 265
2.05 IPS
 
Depth Estimation (Q)
73% 257
2.10 IPS
 
Style Transfer (SP)
100% 2168
2.79 IPS
 
Style Transfer (HP)
100% 1061
1.36 IPS
 
Style Transfer (Q)
98% 650
0.84 IPS
 
Image Super-Resolution (SP)
100% 408
15.1 IPS
 
Image Super-Resolution (HP)
100% 188
6.95 IPS
 
Image Super-Resolution (Q)
99% 140
5.18 IPS
 
Text Classification (SP)
100% 431
575.4 IPS
 
Text Classification (HP)
100% 125
166.6 IPS
 
Text Classification (Q)
97% 107
143.0 IPS
 
Machine Translation (SP)
100% 516
8.88 IPS
 
Machine Translation (HP)
99% 179
3.10 IPS
 
Machine Translation (Q)
59% 139
3.20 IPS
 

Compare

Set Baseline Geekbench 6 now available