Geekbench ML Score

2179
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AArch64

Result Information

Upload Date January 22 2025 06:32 AM
Views 6

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model Microsoft Corporation Microsoft Surface Pro, 11th Edition
Motherboard Microsoft Corporation Microsoft Surface Pro, 11th Edition
Power PlanBalanced
CPU Information
Name Snapdragon(R) X 12-core X1E80100 @ 3.40 GHz
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 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% 1349
252.4 IPS
 
Image Classification (F16)
100% 1216
227.5 IPS
 
Image Classification (I8)
100% 953
178.3 IPS
 
Image Segmentation (F32)
100% 1643
27.4 IPS
 
Image Segmentation (F16)
100% 1662
27.8 IPS
 
Image Segmentation (I8)
98% 1458
24.4 IPS
 
Pose Estimation (F32)
100% 9640
11.7 IPS
 
Pose Estimation (F16)
100% 8334
10.1 IPS
 
Pose Estimation (I8)
100% 7676
9.30 IPS
 
Object Detection (F32)
100% 1213
90.5 IPS
 
Object Detection (F16)
100% 1226
91.5 IPS
 
Object Detection (I8)
71% 898
67.0 IPS
 
Face Detection (F32)
100% 2641
31.4 IPS
 
Face Detection (F16)
100% 2287
27.2 IPS
 
Face Detection (I8)
93% 1975
23.5 IPS
 
Depth Estimation (F32)
100% 5336
41.4 IPS
 
Depth Estimation (F16)
100% 5330
41.3 IPS
 
Depth Estimation (I8)
94% 4553
35.3 IPS
 
Style Transfer (F32)
100% 12512
16.5 IPS
 
Style Transfer (F16)
100% 12426
16.3 IPS
 
Style Transfer (I8)
98% 11697
15.4 IPS
 
Image Super-Resolution (F32)
100% 5025
179.5 IPS
 
Image Super-Resolution (F16)
100% 5096
182.0 IPS
 
Image Super-Resolution (I8)
99% 3538
126.3 IPS
 
Text Classification (F32)
100% 262
376.1 IPS
 
Text Classification (F16)
100% 255
367.0 IPS
 
Text Classification (I8)
98% 233
334.5 IPS
 
Machine Translation (F32)
100% 1075
19.8 IPS
 
Machine Translation (F16)
100% 1022
18.8 IPS
 
Machine Translation (I8)
65% 637
11.7 IPS
 

Compare

Set Baseline Geekbench 6 now available