Geekbench ML Score

1498
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User dynamiteCobra88
Upload Date November 18 2024 11:05 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model Microsoft Corporation Surface Pro 10 for Business
Motherboard Microsoft Corporation Surface Pro 10 for Business
Power PlanBalanced
CPU Information
Name Intel(R) Core(TM) Ultra 5 135U
Topology 1 Processor, 12 Cores, 14 Threads
Identifier GenuineIntel Family 6 Model 170 Stepping 4
Base Frequency 2.10 GHz
Cluster 12 Cores
Cluster 210 Cores
L1 Instruction Cache64.0 KB x 14
L1 Data Cache32.0 KB x 14
L2 Cache2.00 MB x 1
L3 Cache12.0 MB x 1
Memory Information
Size 16.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 579
108.3 IPS
 
Image Classification (F16)
100% 527
98.6 IPS
 
Image Classification (I8)
100% 504
94.3 IPS
 
Image Segmentation (F32)
100% 714
11.9 IPS
 
Image Segmentation (F16)
100% 715
11.9 IPS
 
Image Segmentation (I8)
98% 654
10.9 IPS
 
Pose Estimation (F32)
100% 6814
8.25 IPS
 
Pose Estimation (F16)
100% 6827
8.27 IPS
 
Pose Estimation (I8)
100% 5948
7.20 IPS
 
Object Detection (F32)
100% 495
37.0 IPS
 
Object Detection (F16)
100% 491
36.7 IPS
 
Object Detection (I8)
54% 463
34.6 IPS
 
Face Detection (F32)
100% 978
11.6 IPS
 
Face Detection (F16)
100% 982
11.7 IPS
 
Face Detection (I8)
89% 871
10.4 IPS
 
Depth Estimation (F32)
100% 3290
25.5 IPS
 
Depth Estimation (F16)
100% 3306
25.6 IPS
 
Depth Estimation (I8)
95% 2903
22.5 IPS
 
Style Transfer (F32)
100% 17585
23.1 IPS
 
Style Transfer (F16)
100% 17889
23.5 IPS
 
Style Transfer (I8)
98% 14492
19.1 IPS
 
Image Super-Resolution (F32)
100% 3576
127.7 IPS
 
Image Super-Resolution (F16)
100% 3305
118.0 IPS
 
Image Super-Resolution (I8)
99% 2415
86.2 IPS
 
Text Classification (F32)
90% 373
536.7 IPS
 
Text Classification (F16)
90% 362
520.0 IPS
 
Text Classification (I8)
90% 292
419.5 IPS
 
Machine Translation (F32)
100% 1338
24.6 IPS
 
Machine Translation (F16)
100% 1180
21.7 IPS
 
Machine Translation (I8)
70% 543
10.00 IPS
 

Compare

Set Baseline Geekbench 6 now available