Geekbench ML Score

2157
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AArch64

Result Information

Upload Date January 20 2025 11:18 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% 1248
233.5 IPS
 
Image Classification (F16)
100% 1145
214.2 IPS
 
Image Classification (I8)
100% 954
178.6 IPS
 
Image Segmentation (F32)
100% 1541
25.7 IPS
 
Image Segmentation (F16)
100% 1653
27.6 IPS
 
Image Segmentation (I8)
98% 1456
24.3 IPS
 
Pose Estimation (F32)
100% 9593
11.6 IPS
 
Pose Estimation (F16)
100% 8364
10.1 IPS
 
Pose Estimation (I8)
100% 8647
10.5 IPS
 
Object Detection (F32)
100% 1221
91.2 IPS
 
Object Detection (F16)
100% 1218
90.9 IPS
 
Object Detection (I8)
71% 919
68.6 IPS
 
Face Detection (F32)
100% 2190
26.0 IPS
 
Face Detection (F16)
100% 2453
29.2 IPS
 
Face Detection (I8)
93% 2196
26.1 IPS
 
Depth Estimation (F32)
100% 5200
40.3 IPS
 
Depth Estimation (F16)
100% 5376
41.7 IPS
 
Depth Estimation (I8)
94% 4606
35.7 IPS
 
Style Transfer (F32)
100% 12606
16.6 IPS
 
Style Transfer (F16)
100% 13054
17.2 IPS
 
Style Transfer (I8)
98% 11329
14.9 IPS
 
Image Super-Resolution (F32)
100% 4858
173.5 IPS
 
Image Super-Resolution (F16)
100% 4988
178.2 IPS
 
Image Super-Resolution (I8)
99% 3565
127.3 IPS
 
Text Classification (F32)
100% 256
368.1 IPS
 
Text Classification (F16)
100% 249
357.9 IPS
 
Text Classification (I8)
98% 220
315.8 IPS
 
Machine Translation (F32)
100% 1006
18.5 IPS
 
Machine Translation (F16)
100% 1018
18.7 IPS
 
Machine Translation (I8)
65% 623
11.5 IPS
 

Compare

Set Baseline Geekbench 6 now available