Geekbench AI Score

2011
Single Precision Score
3336
Half Precision Score
6199
Quantized Score
Geekbench AI 1.2.0 for Windows AArch64

Result Information

User DVB
Upload Date December 16 2024 04:00 PM
Views 2

System Information

AI Information
Framework ONNX
Backend CPU
Device Snapdragon(R) X Elite - X1E78100 - Qualcomm(R) Oryon(TM) CPU
System Information
Operating System Microsoft Windows 11 Home (64-bit)
Model LENOVO 83ED
Motherboard LENOVO LNVNB161216
Power PlanBalanced
CPU Information
Name Snapdragon(R) X Elite - X1E78100 - Qualcomm(R) Oryon(TM) CPU
Topology 1 Processor, 12 Cores
Identifier ARMv8 (64-bit) Family 8 Model 1 Revision 201
Base Frequency 3.42 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 717
133.3 IPS
 
Image Classification (HP)
100% 3135
583.0 IPS
 
Image Classification (Q)
99% 6583
1.23 KIPS
 
Image Segmentation (SP)
100% 844
13.7 IPS
 
Image Segmentation (HP)
100% 3260
52.8 IPS
 
Image Segmentation (Q)
98% 2363
38.4 IPS
 
Pose Estimation (SP)
100% 5873
6.85 IPS
 
Pose Estimation (HP)
100% 8240
9.61 IPS
 
Pose Estimation (Q)
94% 16956
19.9 IPS
 
Object Detection (SP)
100% 848
67.2 IPS
 
Object Detection (HP)
99% 2380
189.3 IPS
 
Object Detection (Q)
86% 6438
517.4 IPS
 
Face Detection (SP)
100% 1846
21.9 IPS
 
Face Detection (HP)
100% 6904
82.0 IPS
 
Face Detection (Q)
97% 10764
128.3 IPS
 
Depth Estimation (SP)
100% 2341
18.0 IPS
 
Depth Estimation (HP)
98% 3922
30.3 IPS
 
Depth Estimation (Q)
79% 11519
91.5 IPS
 
Style Transfer (SP)
100% 13980
18.0 IPS
 
Style Transfer (HP)
100% 11407
14.7 IPS
 
Style Transfer (Q)
98% 29098
37.5 IPS
 
Image Super-Resolution (SP)
100% 2142
79.1 IPS
 
Image Super-Resolution (HP)
100% 1612
59.5 IPS
 
Image Super-Resolution (Q)
99% 3848
142.5 IPS
 
Text Classification (SP)
100% 1428
1.91 KIPS
 
Text Classification (HP)
100% 663
884.8 IPS
 
Text Classification (Q)
97% 1212
1.62 KIPS
 
Machine Translation (SP)
100% 1949
33.6 IPS
 
Machine Translation (HP)
99% 2583
44.6 IPS
 
Machine Translation (Q)
65% 2934
59.0 IPS
 

Compare

Set Baseline Geekbench 6 now available