Geekbench AI Score

3117
Single Precision Score
1278
Half Precision Score
3685
Quantized Score
Geekbench AI 1.4.0 for Windows AVX2

Result Information

User xRoach
Upload Date August 23 2025 05:11 PM
Views 3

System Information

AI Information
Framework ONNX
Backend CPU
Device AMD Ryzen 9 3900X
System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model Micro-Star International Co., Ltd. MS-7B85
Motherboard Micro-Star International Co., Ltd. B450 GAMING PRO CARBON AC (MS-7B85)
Power PlanAMD Ryzen High Performance
CPU Information
Name AMD Ryzen 9 3900X
Topology 1 Processor, 12 Cores, 24 Threads
Identifier AuthenticAMD Family 23 Model 113 Stepping 0
Base Frequency 3.80 GHz
Cluster 112 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2682
498.7 IPS
 
Image Classification (HP)
100% 452
84.0 IPS
 
Image Classification (Q)
96% 3321
620.1 IPS
 
Image Segmentation (SP)
100% 948
15.4 IPS
 
Image Segmentation (HP)
100% 540
8.76 IPS
 
Image Segmentation (Q)
97% 4482
72.9 IPS
 
Pose Estimation (SP)
100% 8335
9.73 IPS
 
Pose Estimation (HP)
100% 5671
6.62 IPS
 
Pose Estimation (Q)
86% 8607
10.2 IPS
 
Object Detection (SP)
100% 2575
204.2 IPS
 
Object Detection (HP)
100% 574
45.5 IPS
 
Object Detection (Q)
58% 2480
270.9 IPS
 
Face Detection (SP)
100% 4776
56.7 IPS
 
Face Detection (HP)
100% 1176
14.0 IPS
 
Face Detection (Q)
96% 6779
80.9 IPS
 
Depth Estimation (SP)
100% 7432
57.3 IPS
 
Depth Estimation (HP)
99% 1794
13.8 IPS
 
Depth Estimation (Q)
78% 7719
61.6 IPS
 
Style Transfer (SP)
100% 16144
20.8 IPS
 
Style Transfer (HP)
100% 13782
17.7 IPS
 
Style Transfer (Q)
87% 13116
17.1 IPS
 
Image Super-Resolution (SP)
100% 1839
67.9 IPS
 
Image Super-Resolution (HP)
100% 1580
58.3 IPS
 
Image Super-Resolution (Q)
97% 1444
53.5 IPS
 
Text Classification (SP)
100% 929
1.24 KIPS
 
Text Classification (HP)
100% 475
634.5 IPS
 
Text Classification (Q)
97% 760
1.02 KIPS
 
Machine Translation (SP)
100% 1623
28.0 IPS
 
Machine Translation (HP)
100% 672
11.6 IPS
 
Machine Translation (Q)
68% 1931
37.3 IPS
 

Compare

Set Baseline Geekbench 6 now available