Geekbench ML Score

7880
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date September 18 2024 10:34 AM
Views 3

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model Intel(R) Client Systems NUC12SNKi72
Motherboard Intel Corporation NUC12SNKi72
Power PlanBalanced
CPU Information
Name Intel Core i7-12700H
Topology 1 Processor, 14 Cores, 20 Threads
Identifier GenuineIntel Family 6 Model 154 Stepping 3
Base Frequency 2.30 GHz
Cluster 16 Cores
Cluster 28 Cores
L1 Instruction Cache32.0 KB x 10
L1 Data Cache48.0 KB x 10
L2 Cache1.25 MB x 2
L3 Cache24.0 MB x 1
Memory Information
Size 16.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Arc(TM) A770M Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3898
729.4 IPS
 
Image Classification (F16)
100% 3413
638.6 IPS
 
Image Classification (I8)
99% 3318
620.9 IPS
 
Image Segmentation (F32)
100% 5565
92.9 IPS
 
Image Segmentation (F16)
100% 5951
99.4 IPS
 
Image Segmentation (I8)
98% 5300
88.5 IPS
 
Pose Estimation (F32)
100% 68030
82.4 IPS
 
Pose Estimation (F16)
100% 65305
79.1 IPS
 
Pose Estimation (I8)
100% 55470
67.2 IPS
 
Object Detection (F32)
100% 3789
282.9 IPS
 
Object Detection (F16)
100% 3898
291.0 IPS
 
Object Detection (I8)
60% 3540
264.2 IPS
 
Face Detection (F32)
100% 12006
142.8 IPS
 
Face Detection (F16)
100% 11850
140.9 IPS
 
Face Detection (I8)
88% 8628
102.6 IPS
 
Depth Estimation (F32)
100% 22739
176.3 IPS
 
Depth Estimation (F16)
100% 22673
175.8 IPS
 
Depth Estimation (I8)
95% 19448
150.8 IPS
 
Style Transfer (F32)
100% 137807
181.3 IPS
 
Style Transfer (F16)
100% 129729
170.6 IPS
 
Style Transfer (I8)
98% 103232
135.8 IPS
 
Image Super-Resolution (F32)
100% 11803
421.5 IPS
 
Image Super-Resolution (F16)
100% 11575
413.4 IPS
 
Image Super-Resolution (I8)
99% 9672
345.4 IPS
 
Text Classification (F32)
90% 502
721.4 IPS
 
Text Classification (F16)
90% 544
782.1 IPS
 
Text Classification (I8)
90% 471
677.6 IPS
 
Machine Translation (F32)
100% 1478
27.2 IPS
 
Machine Translation (F16)
100% 1416
26.1 IPS
 
Machine Translation (I8)
70% 976
18.0 IPS
 

Compare

Set Baseline Geekbench 6 now available