Geekbench ML Score

24336
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date March 27 2025 08:04 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 64.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device NVIDIA GeForce RTX 4070 Ti SUPER

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 11935
2.23 KIPS
 
Image Classification (F16)
100% 11715
2.19 KIPS
 
Image Classification (I8)
100% 10028
1.88 KIPS
 
Image Segmentation (F32)
100% 18022
301.0 IPS
 
Image Segmentation (F16)
100% 17165
286.7 IPS
 
Image Segmentation (I8)
98% 15841
264.6 IPS
 
Pose Estimation (F32)
100% 175963
213.1 IPS
 
Pose Estimation (F16)
100% 175764
212.8 IPS
 
Pose Estimation (I8)
100% 157561
190.8 IPS
 
Object Detection (F32)
100% 8269
617.3 IPS
 
Object Detection (F16)
100% 8133
607.1 IPS
 
Object Detection (I8)
56% 7536
562.6 IPS
 
Face Detection (F32)
100% 36740
436.8 IPS
 
Face Detection (F16)
100% 37871
450.3 IPS
 
Face Detection (I8)
89% 31754
377.6 IPS
 
Depth Estimation (F32)
100% 68822
533.7 IPS
 
Depth Estimation (F16)
100% 68065
527.8 IPS
 
Depth Estimation (I8)
94% 54138
419.8 IPS
 
Style Transfer (F32)
100% 310082
407.9 IPS
 
Style Transfer (F16)
100% 310669
408.7 IPS
 
Style Transfer (I8)
98% 273794
360.2 IPS
 
Image Super-Resolution (F32)
100% 46727
1.67 KIPS
 
Image Super-Resolution (F16)
100% 46670
1.67 KIPS
 
Image Super-Resolution (I8)
99% 31853
1.14 KIPS
 
Text Classification (F32)
100% 2956
4.25 KIPS
 
Text Classification (F16)
100% 2998
4.31 KIPS
 
Text Classification (I8)
98% 1833
2.63 KIPS
 
Machine Translation (F32)
100% 4941
90.9 IPS
 
Machine Translation (F16)
100% 4947
91.0 IPS
 
Machine Translation (I8)
70% 2797
51.5 IPS
 

Compare

Set Baseline Geekbench 6 now available