Geekbench AI Score

1603
Single Precision Score
19174
Half Precision Score
51938
Quantized Score
Geekbench AI 1.8.0 for Windows AArch64

Result Information

Upload Date November 20 2026 03:51 PM
Views 3

System Information

AI Information
Framework ONNX
Backend QNN
Device Snapdragon(R) X Plus - X1P42100 - Qualcomm(R) Oryon(TM) CPU
System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model LENOVO Inva
Motherboard LENOVO LNVNB161216
Power PlanTasakaalustatud
CPU Information
Name Snapdragon X Plus X1P-42-100
Topology 1 Processor, 8 Cores
Identifier ARMv8 (64-bit) Family 8 Model 1 Revision 201
Base Frequency 3.24 GHz
Cluster 14 Cores
Cluster 24 Cores
Memory Information
Size 32.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 614
114.2 IPS
 
Image Classification (HP)
100% 13956
2.60 KIPS
 
Image Classification (Q)
99% 29155
5.44 KIPS
 
Image Segmentation (SP)
100% 678
11.0 IPS
 
Image Segmentation (HP)
100% 8620
139.7 IPS
 
Image Segmentation (Q)
98% 24830
403.8 IPS
 
Pose Estimation (SP)
100% 4351
5.08 IPS
 
Pose Estimation (HP)
100% 73241
85.5 IPS
 
Pose Estimation (Q)
95% 260835
305.7 IPS
 
Object Detection (SP)
100% 701
55.6 IPS
 
Object Detection (HP)
100% 13140
1.04 KIPS
 
Object Detection (Q)
92% 26081
2.08 KIPS
 
Face Detection (SP)
100% 1552
18.4 IPS
 
Face Detection (HP)
100% 27089
321.9 IPS
 
Face Detection (Q)
97% 80425
959.0 IPS
 
Depth Estimation (SP)
100% 2076
16.0 IPS
 
Depth Estimation (HP)
99% 46485
358.1 IPS
 
Depth Estimation (Q)
78% 122185
975.2 IPS
 
Style Transfer (SP)
100% 11020
14.2 IPS
 
Style Transfer (HP)
100% 55193
71.0 IPS
 
Style Transfer (Q)
98% 271281
349.8 IPS
 
Image Super-Resolution (SP)
100% 1854
68.5 IPS
 
Image Super-Resolution (HP)
100% 34990
1.29 KIPS
 
Image Super-Resolution (Q)
99% 83225
3.07 KIPS
 
Text Classification (SP)
100% 761
1.02 KIPS
 
Text Classification (HP)
100% 4300
5.74 KIPS
 
Text Classification (Q)
95% 10699
14.3 KIPS
 
Machine Translation (SP)
100% 1770
30.5 IPS
 
Machine Translation (HP)
100% 5550
95.6 IPS
 
Machine Translation (Q)
67% 12221
237.8 IPS
 

Compare

Set Baseline Geekbench AI now available