Geekbench ML Score

314
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

User RG22032
Upload Date March 14 2025 10:03 PM
Views 5

System Information

System Information
Operating System Microsoft Windows 10 Pro (64-bit)
Model Gigabyte Technology Co., Ltd. Z97X-Gaming 7
Motherboard Gigabyte Technology Co., Ltd. Z97X-Gaming 7
Power PlanBalanced
CPU Information
Name Intel Core i7-4790S
Topology 1 Processor, 4 Cores, 8 Threads
Identifier GenuineIntel Family 6 Model 60 Stepping 3
Base Frequency 3.20 GHz
Cluster 14 Cores
L1 Instruction Cache32.0 KB x 4
L1 Data Cache32.0 KB x 4
L2 Cache256 KB x 4
L3 Cache8.00 MB x 1
Memory Information
Size 24.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) HD Graphics 4600

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 188
35.2 IPS
 
Image Classification (F16)
100% 188
35.2 IPS
 
Image Classification (I8)
100% 92
17.2 IPS
 
Image Segmentation (F32)
100% 258
4.32 IPS
 
Image Segmentation (F16)
100% 258
4.30 IPS
 
Image Segmentation (I8)
98% 108
1.80 IPS
 
Pose Estimation (F32)
100% 954
1.16 IPS
 
Pose Estimation (F16)
100% 949
1.15 IPS
 
Pose Estimation (I8)
100% 684
0.83 IPS
 
Object Detection (F32)
100% 221
16.5 IPS
 
Object Detection (F16)
100% 196
14.6 IPS
 
Object Detection (I8)
63% 108
8.07 IPS
 
Face Detection (F32)
100% 392
4.66 IPS
 
Face Detection (F16)
100% 392
4.66 IPS
 
Face Detection (I8)
87% 118
1.40 IPS
 
Depth Estimation (F32)
100% 683
5.30 IPS
 
Depth Estimation (F16)
100% 684
5.31 IPS
 
Depth Estimation (I8)
94% 370
2.87 IPS
 
Style Transfer (F32)
100% 1559
2.05 IPS
 
Style Transfer (F16)
100% 1561
2.05 IPS
 
Style Transfer (I8)
98% 1120
1.47 IPS
 
Image Super-Resolution (F32)
100% 534
19.1 IPS
 
Image Super-Resolution (F16)
100% 537
19.2 IPS
 
Image Super-Resolution (I8)
99% 243
8.69 IPS
 
Text Classification (F32)
100% 232
333.1 IPS
 
Text Classification (F16)
100% 231
332.6 IPS
 
Text Classification (I8)
98% 54
78.0 IPS
 
Machine Translation (F32)
100% 351
6.46 IPS
 
Machine Translation (F16)
100% 338
6.23 IPS
 
Machine Translation (I8)
71% 62
1.14 IPS
 

Compare

Set Baseline Geekbench 6 now available