Geekbench ML Score

13377
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date February 06 2025 11:18 AM
Views 6

System Information

System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model B450M-HDV R4.0
Motherboard ASRock B450M-HDV R4.0
Power PlanBalanced
CPU Information
Name AMD Ryzen 7 5700GE
Topology 1 Processor, 8 Cores, 16 Threads
Identifier AuthenticAMD Family 25 Model 80 Stepping 0
Base Frequency 3.20 GHz
Cluster 18 Cores
L1 Instruction Cache32.0 KB x 8
L1 Data Cache32.0 KB x 8
L2 Cache512 KB x 8
L3 Cache16.0 MB x 1
Memory Information
Size 32.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device AMD Radeon RX 6800 XT

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 8975
1.68 KIPS
 
Image Classification (F16)
100% 8920
1.67 KIPS
 
Image Classification (I8)
100% 7993
1.50 KIPS
 
Image Segmentation (F32)
100% 7886
131.7 IPS
 
Image Segmentation (F16)
100% 8465
141.4 IPS
 
Image Segmentation (I8)
98% 8067
134.7 IPS
 
Pose Estimation (F32)
100% 179349
217.2 IPS
 
Pose Estimation (F16)
100% 180100
218.1 IPS
 
Pose Estimation (I8)
100% 147150
178.2 IPS
 
Object Detection (F32)
100% 2413
180.1 IPS
 
Object Detection (F16)
100% 2425
181.1 IPS
 
Object Detection (I8)
56% 2112
157.7 IPS
 
Face Detection (F32)
100% 25835
307.2 IPS
 
Face Detection (F16)
100% 24396
290.1 IPS
 
Face Detection (I8)
89% 21822
259.5 IPS
 
Depth Estimation (F32)
100% 31390
243.4 IPS
 
Depth Estimation (F16)
100% 31194
241.9 IPS
 
Depth Estimation (I8)
95% 24030
186.4 IPS
 
Style Transfer (F32)
100% 123507
162.5 IPS
 
Style Transfer (F16)
100% 123462
162.4 IPS
 
Style Transfer (I8)
98% 115553
152.0 IPS
 
Image Super-Resolution (F32)
100% 10048
358.8 IPS
 
Image Super-Resolution (F16)
100% 10105
360.9 IPS
 
Image Super-Resolution (I8)
99% 8665
309.5 IPS
 
Text Classification (F32)
100% 3061
4.40 KIPS
 
Text Classification (F16)
100% 3062
4.40 KIPS
 
Text Classification (I8)
98% 2108
3.03 KIPS
 
Machine Translation (F32)
100% 3470
63.9 IPS
 
Machine Translation (F16)
100% 3455
63.6 IPS
 
Machine Translation (I8)
70% 2569
47.3 IPS
 

Compare

Set Baseline Geekbench 6 now available