Geekbench ML Score

2530
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AArch64

Result Information

Upload Date December 10 2024 12:34 AM
Views 3

System Information

System Information
Operating System Microsoft Windows 11 Pro Insider Preview (64-bit)
Model Dell Inc. XPS 13 9345
Motherboard Dell Inc.
Power PlanBalanced
CPU Information
Name Snapdragon(R) X Plus - X1P64100 - Qualcomm(R) Oryon(TM) CPU
Topology 1 Processor, 10 Cores
Identifier ARMv8 (64-bit) Family 8 Model 1 Revision 201
Base Frequency 3.42 GHz
Cluster 16 Cores
Cluster 24 Cores
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Qualcomm(R) Adreno(TM) X1-85 GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1592
297.9 IPS
 
Image Classification (F16)
100% 1538
287.8 IPS
 
Image Classification (I8)
100% 1260
235.9 IPS
 
Image Segmentation (F32)
100% 1841
30.7 IPS
 
Image Segmentation (F16)
100% 1913
31.9 IPS
 
Image Segmentation (I8)
98% 1634
27.3 IPS
 
Pose Estimation (F32)
100% 12278
14.9 IPS
 
Pose Estimation (F16)
100% 12773
15.5 IPS
 
Pose Estimation (I8)
100% 10522
12.7 IPS
 
Object Detection (F32)
100% 1250
93.3 IPS
 
Object Detection (F16)
100% 1343
100.3 IPS
 
Object Detection (I8)
71% 1021
76.2 IPS
 
Face Detection (F32)
100% 3256
38.7 IPS
 
Face Detection (F16)
100% 3243
38.6 IPS
 
Face Detection (I8)
93% 2609
31.0 IPS
 
Depth Estimation (F32)
100% 7024
54.5 IPS
 
Depth Estimation (F16)
100% 7055
54.7 IPS
 
Depth Estimation (I8)
94% 5676
44.0 IPS
 
Style Transfer (F32)
100% 13558
17.8 IPS
 
Style Transfer (F16)
100% 13357
17.6 IPS
 
Style Transfer (I8)
98% 12400
16.3 IPS
 
Image Super-Resolution (F32)
100% 5397
192.7 IPS
 
Image Super-Resolution (F16)
100% 5399
192.8 IPS
 
Image Super-Resolution (I8)
99% 3729
133.2 IPS
 
Text Classification (F32)
100% 296
425.6 IPS
 
Text Classification (F16)
100% 294
422.7 IPS
 
Text Classification (I8)
98% 246
353.5 IPS
 
Machine Translation (F32)
100% 1001
18.4 IPS
 
Machine Translation (F16)
100% 1012
18.6 IPS
 
Machine Translation (I8)
48% 606
11.2 IPS
 

Compare

Set Baseline Geekbench 6 now available