Geekbench AI Score

8259
Single Precision Score
8889
Half Precision Score
5965
Quantized Score
Geekbench AI 1.4.0 Corporate for Windows AVX2

Result Information

Upload Date December 12 2025 10:46 PM
Views 5

System Information

AI Information
Framework ONNX
Backend DirectML
Device Radeon RX 590 Series
System Information
Operating System Microsoft Windows 10 Enterprise (64-bit)
Model System manufacturer System Product Name
Motherboard ASUSTeK COMPUTER INC. TUF B450M-PLUS GAMING
Power PlanHigh performance
CPU Information
Name AMD Ryzen 5 3600
Topology 1 Processor, 6 Cores, 12 Threads
Identifier AuthenticAMD Family 23 Model 113 Stepping 0
Base Frequency 3.95 GHz
Cluster 16 Cores
Memory Information
Size 32.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 3229
600.5 IPS
 
Image Classification (HP)
100% 3866
718.9 IPS
 
Image Classification (Q)
100% 2696
501.3 IPS
 
Image Segmentation (SP)
100% 4167
67.6 IPS
 
Image Segmentation (HP)
100% 4580
74.3 IPS
 
Image Segmentation (Q)
98% 3465
56.3 IPS
 
Pose Estimation (SP)
100% 52654
61.4 IPS
 
Pose Estimation (HP)
100% 57846
67.5 IPS
 
Pose Estimation (Q)
96% 44079
51.6 IPS
 
Object Detection (SP)
100% 3644
289.0 IPS
 
Object Detection (HP)
100% 3892
308.7 IPS
 
Object Detection (Q)
88% 3046
244.2 IPS
 
Face Detection (SP)
100% 9494
112.8 IPS
 
Face Detection (HP)
100% 12703
150.9 IPS
 
Face Detection (Q)
97% 7738
92.3 IPS
 
Depth Estimation (SP)
100% 19863
153.0 IPS
 
Depth Estimation (HP)
99% 22382
172.9 IPS
 
Depth Estimation (Q)
77% 14352
115.0 IPS
 
Style Transfer (SP)
100% 84979
109.2 IPS
 
Style Transfer (HP)
100% 90286
116.1 IPS
 
Style Transfer (Q)
98% 67389
86.9 IPS
 
Image Super-Resolution (SP)
100% 12932
477.5 IPS
 
Image Super-Resolution (HP)
100% 14156
522.7 IPS
 
Image Super-Resolution (Q)
99% 8167
302.4 IPS
 
Text Classification (SP)
100% 1260
1.68 KIPS
 
Text Classification (HP)
100% 1011
1.35 KIPS
 
Text Classification (Q)
97% 745
997.4 IPS
 
Machine Translation (SP)
100% 2192
37.8 IPS
 
Machine Translation (HP)
96% 2105
36.4 IPS
 
Machine Translation (Q)
70% 999
18.7 IPS
 

Compare

Set Baseline Geekbench 6 now available