Geekbench AI Score

3129
Single Precision Score
935
Half Precision Score
6150
Quantized Score
Geekbench AI 1.5.0 for Linux AVX2

Result Information

User yar85
Upload Date October 31 2025 02:31 PM
Views 6
Notes 170W PPT, 12 main threads only (no SMT) via taskset -c 0-11

System Information

AI Information
Framework ONNX
Backend CPU
Device AMD Ryzen 9 5900X
System Information
Operating System Manjaro Linux
Model Micro-Star International Co., Ltd. MS-7C91
Motherboard Micro-Star International Co., Ltd. MAG B550 TOMAHAWK (MS-7C91)
CPU Information
Name AMD Ryzen 9 5900X
Topology 1 Processor, 12 Cores, 24 Threads
Identifier AuthenticAMD Family 25 Model 33 Stepping 0
Base Frequency 5.12 GHz
Cluster 10 Cores
Memory Information
Size 31.26 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1807
336.0 IPS
 
Image Classification (HP)
100% 208
38.7 IPS
 
Image Classification (Q)
94% 6000
1.12 KIPS
 
Image Segmentation (SP)
100% 1620
26.3 IPS
 
Image Segmentation (HP)
100% 351
5.70 IPS
 
Image Segmentation (Q)
98% 2921
47.5 IPS
 
Pose Estimation (SP)
100% 5519
6.44 IPS
 
Pose Estimation (HP)
100% 5109
5.96 IPS
 
Pose Estimation (Q)
86% 16301
19.3 IPS
 
Object Detection (SP)
100% 1716
136.1 IPS
 
Object Detection (HP)
100% 276
21.9 IPS
 
Object Detection (Q)
58% 4655
508.6 IPS
 
Face Detection (SP)
100% 3572
42.4 IPS
 
Face Detection (HP)
100% 447
5.31 IPS
 
Face Detection (Q)
96% 13548
161.6 IPS
 
Depth Estimation (SP)
100% 8716
67.1 IPS
 
Depth Estimation (HP)
99% 1199
9.24 IPS
 
Depth Estimation (Q)
78% 13885
110.8 IPS
 
Style Transfer (SP)
100% 13795
17.7 IPS
 
Style Transfer (HP)
100% 11942
15.4 IPS
 
Style Transfer (Q)
87% 19737
25.7 IPS
 
Image Super-Resolution (SP)
100% 2196
81.1 IPS
 
Image Super-Resolution (HP)
100% 2240
82.7 IPS
 
Image Super-Resolution (Q)
97% 3788
140.4 IPS
 
Text Classification (SP)
100% 1411
1.88 KIPS
 
Text Classification (HP)
100% 587
783.6 IPS
 
Text Classification (Q)
97% 1485
1.99 KIPS
 
Machine Translation (SP)
100% 2442
42.1 IPS
 
Machine Translation (HP)
100% 595
10.2 IPS
 
Machine Translation (Q)
68% 2789
53.9 IPS
 

Compare

Set Baseline Geekbench 6 now available