Geekbench ML Score

2232
ONNX CPU Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User dynamiteCobra88
Upload Date November 21 2024 10:34 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 7
L1 Data Cache48.0 KB x 7
L2 Cache2.00 MB x 1
L3 Cache12.0 MB x 1
Memory Information
Size 16.00 GB
Inference Information
Framework ONNX
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 990
185.3 IPS
 
Image Classification (F16)
100% 945
176.9 IPS
 
Image Classification (I8)
99% 2133
399.1 IPS
 
Image Segmentation (F32)
100% 890
14.9 IPS
 
Image Segmentation (F16)
100% 763
12.7 IPS
 
Image Segmentation (I8)
98% 2330
38.9 IPS
 
Pose Estimation (F32)
100% 3374
4.09 IPS
 
Pose Estimation (F16)
100% 3128
3.79 IPS
 
Pose Estimation (I8)
100% 13832
16.7 IPS
 
Object Detection (F32)
100% 1114
83.2 IPS
 
Object Detection (F16)
100% 1091
81.5 IPS
 
Object Detection (I8)
62% 1202
89.7 IPS
 
Face Detection (F32)
100% 2574
30.6 IPS
 
Face Detection (F16)
100% 2337
27.8 IPS
 
Face Detection (I8)
89% 3127
37.2 IPS
 
Depth Estimation (F32)
100% 3983
30.9 IPS
 
Depth Estimation (F16)
100% 3385
26.3 IPS
 
Depth Estimation (I8)
96% 8506
66.0 IPS
 
Style Transfer (F32)
100% 8824
11.6 IPS
 
Style Transfer (F16)
100% 8798
11.6 IPS
 
Style Transfer (I8)
98% 15184
20.0 IPS
 
Image Super-Resolution (F32)
100% 1721
61.5 IPS
 
Image Super-Resolution (F16)
100% 1801
64.3 IPS
 
Image Super-Resolution (I8)
99% 3309
118.2 IPS
 
Text Classification (F32)
100% 878
1.26 KIPS
 
Text Classification (F16)
100% 854
1.23 KIPS
 
Text Classification (I8)
98% 856
1.23 KIPS
 
Machine Translation (F32)
100% 1174
21.6 IPS
 
Machine Translation (F16)
100% 1180
21.7 IPS
 
Machine Translation (I8)
67% 1853
34.1 IPS
 

Compare

Set Baseline Geekbench 6 now available