Geekbench AI Score

23383
Single Precision Score
25135
Half Precision Score
17031
Quantized Score
Geekbench AI 1.1.0 for Windows AVX2

Result Information

Upload Date September 19 2024 08:23 AM
Views 1

System Information

AI Information
Framework ONNX
Backend DirectML
Device AMD Radeon RX 6800 XT
System Information
Operating System Microsoft Windows 10 Pro (64-bit)
Model Gigabyte Technology Co., Ltd. A520M DS3H
Motherboard Gigabyte Technology Co., Ltd. A520M DS3H
Power PlanBalanced
CPU Information
Name AMD Ryzen 7 5700G
Topology 1 Processor, 8 Cores, 16 Threads
Identifier AuthenticAMD Family 25 Model 80 Stepping 0
Base Frequency 3.80 GHz
Cluster 18 Cores
Memory Information
Size 32.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 9564
1.78 KIPS
 
Image Classification (HP)
100% 8841
1.64 KIPS
 
Image Classification (Q)
100% 7747
1.44 KIPS
 
Image Segmentation (SP)
100% 13759
223.0 IPS
 
Image Segmentation (HP)
100% 11770
190.8 IPS
 
Image Segmentation (Q)
98% 8359
135.9 IPS
 
Pose Estimation (SP)
100% 178881
208.7 IPS
 
Pose Estimation (HP)
100% 259220
302.5 IPS
 
Pose Estimation (Q)
96% 147962
173.4 IPS
 
Object Detection (SP)
100% 10267
814.4 IPS
 
Object Detection (HP)
100% 10265
814.2 IPS
 
Object Detection (Q)
89% 8346
668.3 IPS
 
Face Detection (SP)
100% 26557
315.6 IPS
 
Face Detection (HP)
100% 28399
337.4 IPS
 
Face Detection (Q)
97% 21214
253.0 IPS
 
Depth Estimation (SP)
100% 58920
453.9 IPS
 
Depth Estimation (HP)
99% 64868
499.8 IPS
 
Depth Estimation (Q)
76% 43489
350.6 IPS
 
Style Transfer (SP)
100% 288870
371.3 IPS
 
Style Transfer (HP)
100% 380396
489.0 IPS
 
Style Transfer (Q)
98% 234995
303.0 IPS
 
Image Super-Resolution (SP)
100% 35681
1.32 KIPS
 
Image Super-Resolution (HP)
100% 40902
1.51 KIPS
 
Image Super-Resolution (Q)
99% 27035
1.00 KIPS
 
Text Classification (SP)
100% 3189
4.26 KIPS
 
Text Classification (HP)
100% 3271
4.37 KIPS
 
Text Classification (Q)
97% 2153
2.88 KIPS
 
Machine Translation (SP)
100% 3932
67.7 IPS
 
Machine Translation (HP)
100% 3877
66.8 IPS
 
Machine Translation (Q)
60% 2035
45.4 IPS
 

Compare

Set Baseline Geekbench 6 now available