Geekbench ML Score

2321
ONNX CPU Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User dynamiteCobra88
Upload Date November 07 2024 06:19 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% 969
181.2 IPS
 
Image Classification (F16)
100% 965
180.6 IPS
 
Image Classification (I8)
99% 2136
399.8 IPS
 
Image Segmentation (F32)
100% 833
13.9 IPS
 
Image Segmentation (F16)
100% 923
15.4 IPS
 
Image Segmentation (I8)
98% 2090
34.9 IPS
 
Pose Estimation (F32)
100% 3585
4.34 IPS
 
Pose Estimation (F16)
100% 3426
4.15 IPS
 
Pose Estimation (I8)
100% 14562
17.6 IPS
 
Object Detection (F32)
100% 1052
78.6 IPS
 
Object Detection (F16)
100% 1115
83.2 IPS
 
Object Detection (I8)
62% 1253
93.5 IPS
 
Face Detection (F32)
100% 2663
31.7 IPS
 
Face Detection (F16)
100% 2660
31.6 IPS
 
Face Detection (I8)
89% 3385
40.2 IPS
 
Depth Estimation (F32)
100% 3960
30.7 IPS
 
Depth Estimation (F16)
100% 3856
29.9 IPS
 
Depth Estimation (I8)
96% 9312
72.2 IPS
 
Style Transfer (F32)
100% 9187
12.1 IPS
 
Style Transfer (F16)
100% 9054
11.9 IPS
 
Style Transfer (I8)
98% 15090
19.8 IPS
 
Image Super-Resolution (F32)
100% 2050
73.2 IPS
 
Image Super-Resolution (F16)
100% 1914
68.4 IPS
 
Image Super-Resolution (I8)
99% 3443
123.0 IPS
 
Text Classification (F32)
100% 1058
1.52 KIPS
 
Text Classification (F16)
100% 1051
1.51 KIPS
 
Text Classification (I8)
98% 422
606.9 IPS
 
Machine Translation (F32)
100% 1308
24.1 IPS
 
Machine Translation (F16)
100% 1342
24.7 IPS
 
Machine Translation (I8)
67% 2333
42.9 IPS
 

Compare

Set Baseline Geekbench 6 now available