Geekbench AI Score

2295
Single Precision Score
3031
Half Precision Score
1768
Quantized Score
Geekbench AI 1.7.0 for Windows AVX2

Result Information

User ju83
Upload Date September 28 2026 06:55 PM
Views 8

System Information

AI Information
Framework ONNX
Backend DirectML
Device AMD Radeon(TM) Vega 8 Graphics
System Information
Operating System Microsoft Windows 11 Famille (64-bit)
Model Micro-Star International Co., Ltd MS-7B86
Motherboard Micro-Star International Co., Ltd B450-A PRO MAX (MS-7B86)
Power Planconomie d'nergie
CPU Information
Name AMD Ryzen 3 3200G
Topology 1 Processor, 4 Cores
Identifier AuthenticAMD Family 23 Model 24 Stepping 1
Base Frequency 3.60 GHz
Cluster 14 Cores
Memory Information
Size 8.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 973
181.0 IPS
 
Image Classification (HP)
100% 1229
228.6 IPS
 
Image Classification (Q)
100% 876
162.8 IPS
 
Image Segmentation (SP)
100% 1028
16.7 IPS
 
Image Segmentation (HP)
100% 1201
19.5 IPS
 
Image Segmentation (Q)
98% 895
14.6 IPS
 
Pose Estimation (SP)
100% 8406
9.81 IPS
 
Pose Estimation (HP)
100% 15214
17.8 IPS
 
Pose Estimation (Q)
96% 7091
8.31 IPS
 
Object Detection (SP)
100% 1062
84.2 IPS
 
Object Detection (HP)
100% 1299
103.0 IPS
 
Object Detection (Q)
88% 962
77.1 IPS
 
Face Detection (SP)
100% 2372
28.2 IPS
 
Face Detection (HP)
100% 3294
39.1 IPS
 
Face Detection (Q)
97% 2026
24.2 IPS
 
Depth Estimation (SP)
100% 5475
42.2 IPS
 
Depth Estimation (HP)
99% 7781
59.9 IPS
 
Depth Estimation (Q)
77% 4234
33.8 IPS
 
Style Transfer (SP)
100% 14570
18.7 IPS
 
Style Transfer (HP)
100% 24104
31.0 IPS
 
Style Transfer (Q)
98% 11713
15.1 IPS
 
Image Super-Resolution (SP)
100% 3209
118.5 IPS
 
Image Super-Resolution (HP)
100% 4749
175.4 IPS
 
Image Super-Resolution (Q)
99% 2185
80.9 IPS
 
Text Classification (SP)
100% 670
894.8 IPS
 
Text Classification (HP)
100% 641
855.0 IPS
 
Text Classification (Q)
97% 471
630.9 IPS
 
Machine Translation (SP)
100% 1117
19.2 IPS
 
Machine Translation (HP)
100% 1196
20.6 IPS
 
Machine Translation (Q)
70% 541
10.1 IPS
 

Compare

Set Baseline Geekbench AI now available