Geekbench ML Score

23843
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date March 27 2025 08:42 AM
Views 4

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 128.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device NVIDIA GeForce RTX 4070 Ti SUPER

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 11121
2.08 KIPS
 
Image Classification (F16)
100% 11411
2.14 KIPS
 
Image Classification (I8)
100% 9725
1.82 KIPS
 
Image Segmentation (F32)
100% 17051
284.8 IPS
 
Image Segmentation (F16)
100% 16986
283.7 IPS
 
Image Segmentation (I8)
98% 15119
252.5 IPS
 
Pose Estimation (F32)
100% 175518
212.5 IPS
 
Pose Estimation (F16)
100% 175056
212.0 IPS
 
Pose Estimation (I8)
100% 157273
190.5 IPS
 
Object Detection (F32)
100% 8393
626.6 IPS
 
Object Detection (F16)
100% 8216
613.3 IPS
 
Object Detection (I8)
56% 7693
574.3 IPS
 
Face Detection (F32)
100% 34382
408.8 IPS
 
Face Detection (F16)
100% 37158
441.8 IPS
 
Face Detection (I8)
89% 30982
368.4 IPS
 
Depth Estimation (F32)
100% 71145
551.7 IPS
 
Depth Estimation (F16)
100% 67975
527.1 IPS
 
Depth Estimation (I8)
94% 53527
415.1 IPS
 
Style Transfer (F32)
100% 311224
409.4 IPS
 
Style Transfer (F16)
100% 309900
407.6 IPS
 
Style Transfer (I8)
98% 273404
359.6 IPS
 
Image Super-Resolution (F32)
100% 43553
1.56 KIPS
 
Image Super-Resolution (F16)
100% 43102
1.54 KIPS
 
Image Super-Resolution (I8)
99% 32920
1.18 KIPS
 
Text Classification (F32)
100% 2906
4.18 KIPS
 
Text Classification (F16)
100% 2762
3.97 KIPS
 
Text Classification (I8)
98% 1787
2.57 KIPS
 
Machine Translation (F32)
100% 4784
88.0 IPS
 
Machine Translation (F16)
100% 4814
88.6 IPS
 
Machine Translation (I8)
70% 2743
50.5 IPS
 

Compare

Set Baseline Geekbench 6 now available