Geekbench ML Score

1502
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User dynamiteCobra88
Upload Date November 18 2024 10:58 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% 564
105.6 IPS
 
Image Classification (F16)
100% 553
103.5 IPS
 
Image Classification (I8)
100% 482
90.2 IPS
 
Image Segmentation (F32)
100% 728
12.2 IPS
 
Image Segmentation (F16)
100% 711
11.9 IPS
 
Image Segmentation (I8)
98% 669
11.2 IPS
 
Pose Estimation (F32)
100% 6789
8.22 IPS
 
Pose Estimation (F16)
100% 6882
8.33 IPS
 
Pose Estimation (I8)
100% 5902
7.15 IPS
 
Object Detection (F32)
100% 511
38.1 IPS
 
Object Detection (F16)
100% 509
38.0 IPS
 
Object Detection (I8)
54% 502
37.5 IPS
 
Face Detection (F32)
100% 998
11.9 IPS
 
Face Detection (F16)
100% 970
11.5 IPS
 
Face Detection (I8)
89% 878
10.4 IPS
 
Depth Estimation (F32)
100% 3381
26.2 IPS
 
Depth Estimation (F16)
100% 3312
25.7 IPS
 
Depth Estimation (I8)
95% 2865
22.2 IPS
 
Style Transfer (F32)
100% 17614
23.2 IPS
 
Style Transfer (F16)
100% 18152
23.9 IPS
 
Style Transfer (I8)
98% 14687
19.3 IPS
 
Image Super-Resolution (F32)
100% 3527
126.0 IPS
 
Image Super-Resolution (F16)
100% 3447
123.1 IPS
 
Image Super-Resolution (I8)
99% 2273
81.2 IPS
 
Text Classification (F32)
90% 458
658.3 IPS
 
Text Classification (F16)
90% 366
526.2 IPS
 
Text Classification (I8)
90% 243
349.8 IPS
 
Machine Translation (F32)
100% 1199
22.1 IPS
 
Machine Translation (F16)
100% 1198
22.1 IPS
 
Machine Translation (I8)
70% 523
9.63 IPS
 

Compare

Set Baseline Geekbench 6 now available