Geekbench ML Score

2429
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date July 19 2024 07:10 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 (64-bit)
Model AAEON MIX-MTLD1
Motherboard AAEON MIX-MTLD1
CPU Information
Name Intel Core Ultra 5 125H
Topology 1 Processor, 14 Cores, 18 Threads
Identifier GenuineIntel Family 6 Model 170 Stepping 4
Base Frequency 3.60 GHz
Cluster 14 Cores
Cluster 210 Cores
L1 Instruction Cache64.0 KB x 9
L1 Data Cache48.0 KB x 9
L2 Cache2.00 MB x 2
L3 Cache18.0 MB x 1
Memory Information
Size 8.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Arc(TM) Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1410
263.8 IPS
 
Image Classification (F16)
100% 1427
267.0 IPS
 
Image Classification (I8)
100% 1120
209.5 IPS
 
Image Segmentation (F32)
100% 1382
23.1 IPS
 
Image Segmentation (F16)
100% 1362
22.7 IPS
 
Image Segmentation (I8)
98% 1151
19.2 IPS
 
Pose Estimation (F32)
100% 8667
10.5 IPS
 
Pose Estimation (F16)
100% 8956
10.8 IPS
 
Pose Estimation (I8)
100% 6809
8.25 IPS
 
Object Detection (F32)
100% 1339
99.9 IPS
 
Object Detection (F16)
100% 1415
105.7 IPS
 
Object Detection (I8)
54% 1048
78.2 IPS
 
Face Detection (F32)
100% 1923
22.9 IPS
 
Face Detection (F16)
100% 1878
22.3 IPS
 
Face Detection (I8)
89% 1323
15.7 IPS
 
Depth Estimation (F32)
100% 6041
46.8 IPS
 
Depth Estimation (F16)
100% 5810
45.1 IPS
 
Depth Estimation (I8)
95% 4396
34.1 IPS
 
Style Transfer (F32)
100% 23745
31.2 IPS
 
Style Transfer (F16)
100% 23318
30.7 IPS
 
Style Transfer (I8)
98% 15745
20.7 IPS
 
Image Super-Resolution (F32)
100% 4662
166.5 IPS
 
Image Super-Resolution (F16)
100% 4574
163.4 IPS
 
Image Super-Resolution (I8)
99% 2697
96.3 IPS
 
Text Classification (F32)
90% 730
1.05 KIPS
 
Text Classification (F16)
90% 751
1.08 KIPS
 
Text Classification (I8)
90% 521
748.7 IPS
 
Machine Translation (F32)
100% 1028
18.9 IPS
 
Machine Translation (F16)
100% 1040
19.1 IPS
 
Machine Translation (I8)
70% 635
11.7 IPS
 

Compare

Set Baseline Geekbench 6 now available