Geekbench ML Score

2276
ONNX CPU Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User dynamiteCobra88
Upload Date November 20 2024 02:51 PM
Views 4

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% 923
172.6 IPS
 
Image Classification (F16)
100% 882
165.0 IPS
 
Image Classification (I8)
99% 2157
403.7 IPS
 
Image Segmentation (F32)
100% 671
11.2 IPS
 
Image Segmentation (F16)
100% 854
14.3 IPS
 
Image Segmentation (I8)
98% 2320
38.8 IPS
 
Pose Estimation (F32)
100% 3385
4.10 IPS
 
Pose Estimation (F16)
100% 3342
4.05 IPS
 
Pose Estimation (I8)
100% 13657
16.5 IPS
 
Object Detection (F32)
100% 1120
83.6 IPS
 
Object Detection (F16)
100% 999
74.6 IPS
 
Object Detection (I8)
62% 982
73.3 IPS
 
Face Detection (F32)
100% 2300
27.4 IPS
 
Face Detection (F16)
100% 2542
30.2 IPS
 
Face Detection (I8)
89% 3295
39.2 IPS
 
Depth Estimation (F32)
100% 4070
31.6 IPS
 
Depth Estimation (F16)
100% 3869
30.0 IPS
 
Depth Estimation (I8)
96% 8688
67.4 IPS
 
Style Transfer (F32)
100% 8876
11.7 IPS
 
Style Transfer (F16)
100% 8802
11.6 IPS
 
Style Transfer (I8)
98% 14624
19.2 IPS
 
Image Super-Resolution (F32)
100% 1816
64.9 IPS
 
Image Super-Resolution (F16)
100% 1958
69.9 IPS
 
Image Super-Resolution (I8)
99% 3513
125.4 IPS
 
Text Classification (F32)
100% 937
1.35 KIPS
 
Text Classification (F16)
100% 1038
1.49 KIPS
 
Text Classification (I8)
98% 930
1.34 KIPS
 
Machine Translation (F32)
100% 1328
24.4 IPS
 
Machine Translation (F16)
100% 1309
24.1 IPS
 
Machine Translation (I8)
67% 2217
40.8 IPS
 

Compare

Set Baseline Geekbench 6 now available