Geekbench ML Score

2173
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AArch64

Result Information

Upload Date January 20 2025 10:26 AM
Views 2

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% 1256
235.1 IPS
 
Image Classification (F16)
100% 1210
226.5 IPS
 
Image Classification (I8)
100% 1194
223.4 IPS
 
Image Segmentation (F32)
100% 1529
25.5 IPS
 
Image Segmentation (F16)
100% 1712
28.6 IPS
 
Image Segmentation (I8)
98% 1473
24.6 IPS
 
Pose Estimation (F32)
100% 8387
10.2 IPS
 
Pose Estimation (F16)
100% 9336
11.3 IPS
 
Pose Estimation (I8)
100% 8552
10.4 IPS
 
Object Detection (F32)
100% 1210
90.3 IPS
 
Object Detection (F16)
100% 1085
81.0 IPS
 
Object Detection (I8)
71% 1081
80.7 IPS
 
Face Detection (F32)
100% 2306
27.4 IPS
 
Face Detection (F16)
100% 2421
28.8 IPS
 
Face Detection (I8)
93% 1942
23.1 IPS
 
Depth Estimation (F32)
100% 5239
40.6 IPS
 
Depth Estimation (F16)
100% 5339
41.4 IPS
 
Depth Estimation (I8)
94% 4635
35.9 IPS
 
Style Transfer (F32)
100% 12873
16.9 IPS
 
Style Transfer (F16)
100% 12472
16.4 IPS
 
Style Transfer (I8)
98% 11723
15.4 IPS
 
Image Super-Resolution (F32)
100% 4969
177.5 IPS
 
Image Super-Resolution (F16)
100% 4899
175.0 IPS
 
Image Super-Resolution (I8)
99% 3600
128.6 IPS
 
Text Classification (F32)
100% 247
354.8 IPS
 
Text Classification (F16)
100% 258
370.4 IPS
 
Text Classification (I8)
98% 202
290.9 IPS
 
Machine Translation (F32)
100% 1045
19.2 IPS
 
Machine Translation (F16)
100% 1010
18.6 IPS
 
Machine Translation (I8)
65% 625
11.5 IPS
 

Compare

Set Baseline Geekbench 6 now available