Geekbench AI Score

40954
Single Precision Score
57627
Half Precision Score
30809
Quantized Score
Geekbench AI 1.5.0 for Windows AVX2

Result Information

User Liosnel
Upload Date October 22 2025 01:21 AM
Views 15

System Information

AI Information
Framework ONNX
Backend DirectML
Device NVIDIA GeForce RTX 4090
System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model ASRock X870E Taichi Lite
Motherboard ASRock X870E Taichi Lite
Power PlanBalanced
CPU Information
Name AMD Ryzen 9 7950X
Topology 1 Processor, 16 Cores, 32 Threads
Identifier AuthenticAMD Family 25 Model 97 Stepping 2
Base Frequency 4.50 GHz
Cluster 116 Cores
Memory Information
Size 32.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 14626
2.72 KIPS
 
Image Classification (HP)
99% 19423
3.62 KIPS
 
Image Classification (Q)
100% 12328
2.29 KIPS
 
Image Segmentation (SP)
100% 28488
461.8 IPS
 
Image Segmentation (HP)
100% 38276
620.5 IPS
 
Image Segmentation (Q)
98% 26752
435.0 IPS
 
Pose Estimation (SP)
100% 297448
347.1 IPS
 
Pose Estimation (HP)
100% 604365
705.2 IPS
 
Pose Estimation (Q)
96% 261183
306.0 IPS
 
Object Detection (SP)
100% 20352
1.61 KIPS
 
Object Detection (HP)
100% 26914
2.13 KIPS
 
Object Detection (Q)
86% 16900
1.36 KIPS
 
Face Detection (SP)
100% 60858
723.1 IPS
 
Face Detection (HP)
100% 77660
922.8 IPS
 
Face Detection (Q)
97% 51424
613.1 IPS
 
Depth Estimation (SP)
100% 104686
806.5 IPS
 
Depth Estimation (HP)
99% 169502
1.31 KIPS
 
Depth Estimation (Q)
77% 75479
603.7 IPS
 
Style Transfer (SP)
100% 600388
771.8 IPS
 
Style Transfer (HP)
100% 1148682
1.48 KIPS
 
Style Transfer (Q)
98% 495706
639.2 IPS
 
Image Super-Resolution (SP)
100% 63960
2.36 KIPS
 
Image Super-Resolution (HP)
100% 85313
3.15 KIPS
 
Image Super-Resolution (Q)
99% 47425
1.76 KIPS
 
Text Classification (SP)
100% 3380
4.51 KIPS
 
Text Classification (HP)
99% 4100
5.47 KIPS
 
Text Classification (Q)
97% 2067
2.77 KIPS
 
Machine Translation (SP)
100% 6365
109.6 IPS
 
Machine Translation (HP)
100% 6316
108.8 IPS
 
Machine Translation (Q)
70% 2807
52.6 IPS
 

Compare

Set Baseline Geekbench AI now available