Geekbench ML Score

1222
ONNX CPU Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User dynamiteCobra88
Upload Date November 18 2024 10:54 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 CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 474
88.7 IPS
 
Image Classification (F16)
100% 478
89.5 IPS
 
Image Classification (I8)
99% 1035
193.7 IPS
 
Image Segmentation (F32)
100% 427
7.13 IPS
 
Image Segmentation (F16)
100% 470
7.84 IPS
 
Image Segmentation (I8)
98% 1122
18.7 IPS
 
Pose Estimation (F32)
100% 2583
3.13 IPS
 
Pose Estimation (F16)
100% 2497
3.02 IPS
 
Pose Estimation (I8)
100% 6792
8.22 IPS
 
Object Detection (F32)
100% 524
39.1 IPS
 
Object Detection (F16)
100% 527
39.3 IPS
 
Object Detection (I8)
62% 543
40.5 IPS
 
Face Detection (F32)
100% 1489
17.7 IPS
 
Face Detection (F16)
100% 1495
17.8 IPS
 
Face Detection (I8)
89% 1676
19.9 IPS
 
Depth Estimation (F32)
100% 2413
18.7 IPS
 
Depth Estimation (F16)
100% 2478
19.2 IPS
 
Depth Estimation (I8)
96% 4360
33.8 IPS
 
Style Transfer (F32)
100% 5050
6.64 IPS
 
Style Transfer (F16)
100% 5048
6.64 IPS
 
Style Transfer (I8)
98% 8068
10.6 IPS
 
Image Super-Resolution (F32)
100% 920
32.9 IPS
 
Image Super-Resolution (F16)
100% 938
33.5 IPS
 
Image Super-Resolution (I8)
99% 1546
55.2 IPS
 
Text Classification (F32)
100% 481
691.4 IPS
 
Text Classification (F16)
100% 486
697.8 IPS
 
Text Classification (I8)
98% 418
600.2 IPS
 
Machine Translation (F32)
100% 658
12.1 IPS
 
Machine Translation (F16)
100% 659
12.1 IPS
 
Machine Translation (I8)
67% 1062
19.5 IPS
 

Compare

Set Baseline Geekbench 6 now available