Geekbench ML Score

3632
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date November 23 2025 02:44 PM
Views 11

System Information

System Information
Operating System Microsoft Windows 11 Home Single Language (64-bit)
Model LENOVO 83F5
Motherboard LENOVO LNVNB161216
Power PlanBalanced
CPU Information
Name Intel Core Ultra 9 275HX
Topology 1 Processor, 24 Cores
Identifier GenuineIntel Family 6 Model 198 Stepping 2
Base Frequency 2.70 GHz
Cluster 18 Cores
Cluster 216 Cores
L1 Instruction Cache64.0 KB x 12
L1 Data Cache48.0 KB x 12
L2 Cache3.00 MB x 3
L3 Cache36.0 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Graphics

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2356
440.9 IPS
 
Image Classification (F16)
100% 2351
439.9 IPS
 
Image Classification (I8)
100% 1707
319.4 IPS
 
Image Segmentation (F32)
100% 2975
49.7 IPS
 
Image Segmentation (F16)
100% 3005
50.2 IPS
 
Image Segmentation (I8)
98% 2048
34.2 IPS
 
Pose Estimation (F32)
100% 8280
10.0 IPS
 
Pose Estimation (F16)
100% 8247
9.99 IPS
 
Pose Estimation (I8)
100% 7372
8.93 IPS
 
Object Detection (F32)
100% 2314
172.7 IPS
 
Object Detection (F16)
100% 2264
169.1 IPS
 
Object Detection (I8)
54% 1769
132.1 IPS
 
Face Detection (F32)
100% 4737
56.3 IPS
 
Face Detection (F16)
100% 4862
57.8 IPS
 
Face Detection (I8)
89% 2966
35.3 IPS
 
Depth Estimation (F32)
100% 8927
69.2 IPS
 
Depth Estimation (F16)
100% 8981
69.6 IPS
 
Depth Estimation (I8)
95% 6742
52.3 IPS
 
Style Transfer (F32)
100% 24915
32.8 IPS
 
Style Transfer (F16)
100% 25304
33.3 IPS
 
Style Transfer (I8)
98% 20026
26.3 IPS
 
Image Super-Resolution (F32)
100% 4903
175.1 IPS
 
Image Super-Resolution (F16)
100% 4919
175.7 IPS
 
Image Super-Resolution (I8)
99% 3236
115.6 IPS
 
Text Classification (F32)
100% 1161
1.67 KIPS
 
Text Classification (F16)
100% 1139
1.64 KIPS
 
Text Classification (I8)
98% 650
933.8 IPS
 
Machine Translation (F32)
100% 1674
30.8 IPS
 
Machine Translation (F16)
100% 1685
31.0 IPS
 
Machine Translation (I8)
70% 897
16.5 IPS
 

Compare

Set Baseline Geekbench 6 now available