Geekbench ML Score

24045
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date March 27 2025 07:18 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model LENOVO INVALID
Motherboard LENOVO 3784
Power PlanLenovo Default
CPU Information
Name Intel(R) Core(TM) Ultra 7 265K
Topology 1 Processor, 20 Cores
Identifier GenuineIntel Family 6 Model 198 Stepping 2
Base Frequency 3.90 GHz
Cluster 18 Cores
Cluster 212 Cores
L1 Instruction Cache64.0 KB x 10
L1 Data Cache48.0 KB x 10
L2 Cache3.00 MB x 2
L3 Cache30.0 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device NVIDIA GeForce RTX 4070 Ti SUPER

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 11673
2.18 KIPS
 
Image Classification (F16)
100% 11531
2.16 KIPS
 
Image Classification (I8)
100% 10080
1.89 KIPS
 
Image Segmentation (F32)
100% 17134
286.2 IPS
 
Image Segmentation (F16)
100% 16694
278.8 IPS
 
Image Segmentation (I8)
98% 15236
254.5 IPS
 
Pose Estimation (F32)
100% 176237
213.4 IPS
 
Pose Estimation (F16)
100% 174793
211.7 IPS
 
Pose Estimation (I8)
100% 156890
190.0 IPS
 
Object Detection (F32)
100% 8431
629.4 IPS
 
Object Detection (F16)
100% 8266
617.1 IPS
 
Object Detection (I8)
56% 7725
576.7 IPS
 
Face Detection (F32)
100% 35929
427.2 IPS
 
Face Detection (F16)
100% 37082
440.9 IPS
 
Face Detection (I8)
89% 30186
358.9 IPS
 
Depth Estimation (F32)
100% 70734
548.5 IPS
 
Depth Estimation (F16)
100% 67645
524.6 IPS
 
Depth Estimation (I8)
94% 53889
417.9 IPS
 
Style Transfer (F32)
100% 313001
411.7 IPS
 
Style Transfer (F16)
100% 308475
405.8 IPS
 
Style Transfer (I8)
98% 276302
363.5 IPS
 
Image Super-Resolution (F32)
100% 43231
1.54 KIPS
 
Image Super-Resolution (F16)
100% 42879
1.53 KIPS
 
Image Super-Resolution (I8)
99% 32768
1.17 KIPS
 
Text Classification (F32)
100% 3006
4.32 KIPS
 
Text Classification (F16)
100% 2982
4.29 KIPS
 
Text Classification (I8)
98% 1826
2.62 KIPS
 
Machine Translation (F32)
100% 4822
88.7 IPS
 
Machine Translation (F16)
100% 4825
88.8 IPS
 
Machine Translation (I8)
70% 2741
50.4 IPS
 

Compare

Set Baseline Geekbench 6 now available