Geekbench ML Score

1220
ONNX CPU Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User dynamiteCobra88
Upload Date November 18 2024 10:50 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% 480
89.9 IPS
 
Image Classification (F16)
100% 487
91.1 IPS
 
Image Classification (I8)
99% 1042
195.1 IPS
 
Image Segmentation (F32)
100% 365
6.09 IPS
 
Image Segmentation (F16)
100% 461
7.70 IPS
 
Image Segmentation (I8)
98% 1082
18.1 IPS
 
Pose Estimation (F32)
100% 2571
3.11 IPS
 
Pose Estimation (F16)
100% 2474
3.00 IPS
 
Pose Estimation (I8)
100% 7381
8.94 IPS
 
Object Detection (F32)
100% 541
40.4 IPS
 
Object Detection (F16)
100% 539
40.2 IPS
 
Object Detection (I8)
62% 582
43.5 IPS
 
Face Detection (F32)
100% 1354
16.1 IPS
 
Face Detection (F16)
100% 1460
17.4 IPS
 
Face Detection (I8)
89% 1646
19.6 IPS
 
Depth Estimation (F32)
100% 2269
17.6 IPS
 
Depth Estimation (F16)
100% 2263
17.5 IPS
 
Depth Estimation (I8)
96% 4656
36.1 IPS
 
Style Transfer (F32)
100% 5290
6.96 IPS
 
Style Transfer (F16)
100% 5358
7.05 IPS
 
Style Transfer (I8)
98% 9599
12.6 IPS
 
Image Super-Resolution (F32)
100% 897
32.0 IPS
 
Image Super-Resolution (F16)
100% 865
30.9 IPS
 
Image Super-Resolution (I8)
99% 1516
54.1 IPS
 
Text Classification (F32)
100% 478
686.5 IPS
 
Text Classification (F16)
100% 482
692.0 IPS
 
Text Classification (I8)
98% 429
616.8 IPS
 
Machine Translation (F32)
100% 657
12.1 IPS
 
Machine Translation (F16)
100% 656
12.1 IPS
 
Machine Translation (I8)
67% 1061
19.5 IPS
 

Compare

Set Baseline Geekbench 6 now available