Geekbench ML Score

13635
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date August 21 2024 02:02 AM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model LENOVO 21KWZC48US
Motherboard LENOVO 21KWZC48US
Power PlanBalanced
CPU Information
Name Intel Core Ultra 9 185H
Topology 1 Processor, 16 Cores, 22 Threads
Identifier GenuineIntel Family 6 Model 170 Stepping 4
Base Frequency 2.30 GHz
Cluster 16 Cores
Cluster 210 Cores
L1 Instruction Cache64.0 KB x 11
L1 Data Cache48.0 KB x 11
L2 Cache2.00 MB x 2
L3 Cache24.0 MB x 1
Memory Information
Size 64.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device NVIDIA RTX 3000 Ada Generation Laptop GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6667
1.25 KIPS
 
Image Classification (F16)
100% 6892
1.29 KIPS
 
Image Classification (I8)
100% 6084
1.14 KIPS
 
Image Segmentation (F32)
100% 8711
145.5 IPS
 
Image Segmentation (F16)
100% 8771
146.5 IPS
 
Image Segmentation (I8)
98% 8187
136.7 IPS
 
Pose Estimation (F32)
100% 99086
120.0 IPS
 
Pose Estimation (F16)
100% 98432
119.2 IPS
 
Pose Estimation (I8)
100% 85581
103.6 IPS
 
Object Detection (F32)
100% 4845
361.7 IPS
 
Object Detection (F16)
100% 4676
349.1 IPS
 
Object Detection (I8)
63% 4368
326.1 IPS
 
Face Detection (F32)
100% 17119
203.5 IPS
 
Face Detection (F16)
100% 17361
206.4 IPS
 
Face Detection (I8)
89% 15226
181.0 IPS
 
Depth Estimation (F32)
100% 37722
292.5 IPS
 
Depth Estimation (F16)
100% 37268
289.0 IPS
 
Depth Estimation (I8)
94% 32209
249.8 IPS
 
Style Transfer (F32)
100% 143002
188.1 IPS
 
Style Transfer (F16)
100% 144101
189.6 IPS
 
Style Transfer (I8)
98% 132000
173.6 IPS
 
Image Super-Resolution (F32)
100% 28312
1.01 KIPS
 
Image Super-Resolution (F16)
100% 27058
966.3 IPS
 
Image Super-Resolution (I8)
99% 21297
760.6 IPS
 
Text Classification (F32)
100% 1953
2.81 KIPS
 
Text Classification (F16)
100% 1908
2.74 KIPS
 
Text Classification (I8)
98% 1308
1.88 KIPS
 
Machine Translation (F32)
100% 3167
58.3 IPS
 
Machine Translation (F16)
100% 3172
58.4 IPS
 
Machine Translation (I8)
70% 1706
31.4 IPS
 

Compare

Set Baseline Geekbench 6 now available