Geekbench AI Score

4766
Single Precision Score
910
Half Precision Score
5614
Quantized Score
Geekbench AI 1.0.0 for Windows AVX2

Result Information

User Rendus
Upload Date August 16 2024 04:14 AM
Views 19

System Information

AI Information
Framework ONNX
Backend CPU
Device Intel Core i9-13900K
System Information
Operating System Microsoft Windows 11 Pro (64-bit)
Model Gigabyte Technology Co., Ltd. Z790 AORUS MASTER
Motherboard Gigabyte Technology Co., Ltd. Z790 AORUS MASTER
Power PlanHigh performance
CPU Information
Name Intel Core i9-13900K
Topology 1 Processor, 24 Cores, 32 Threads
Identifier GenuineIntel Family 6 Model 183 Stepping 1
Base Frequency 3.00 GHz
Cluster 18 Cores
Cluster 216 Cores
Memory Information
Size 96.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2524
469.4 IPS
 
Image Classification (HP)
100% 159
29.6 IPS
 
Image Classification (Q)
99% 4603
858.5 IPS
 
Image Segmentation (SP)
100% 2208
35.8 IPS
 
Image Segmentation (HP)
100% 303
4.91 IPS
 
Image Segmentation (Q)
98% 3399
55.3 IPS
 
Pose Estimation (SP)
100% 12358
14.4 IPS
 
Pose Estimation (HP)
100% 5207
6.08 IPS
 
Pose Estimation (Q)
95% 37989
44.5 IPS
 
Object Detection (SP)
100% 2947
233.7 IPS
 
Object Detection (HP)
100% 239
18.9 IPS
 
Object Detection (Q)
88% 2442
195.8 IPS
 
Face Detection (SP)
100% 5242
62.3 IPS
 
Face Detection (HP)
100% 345
4.10 IPS
 
Face Detection (Q)
97% 5415
64.6 IPS
 
Depth Estimation (SP)
100% 10901
84.0 IPS
 
Depth Estimation (HP)
99% 1046
8.06 IPS
 
Depth Estimation (Q)
76% 12033
96.9 IPS
 
Style Transfer (SP)
100% 26896
34.6 IPS
 
Style Transfer (HP)
100% 12881
16.6 IPS
 
Style Transfer (Q)
98% 30545
39.4 IPS
 
Image Super-Resolution (SP)
100% 4451
164.3 IPS
 
Image Super-Resolution (HP)
100% 2441
90.1 IPS
 
Image Super-Resolution (Q)
99% 5673
210.1 IPS
 
Text Classification (SP)
100% 1943
2.59 KIPS
 
Text Classification (HP)
100% 772
1.03 KIPS
 
Text Classification (Q)
97% 696
932.8 IPS
 
Machine Translation (SP)
100% 2243
38.6 IPS
 
Machine Translation (HP)
100% 745
12.8 IPS
 
Machine Translation (Q)
60% 2729
60.9 IPS
 

Compare

Set Baseline Geekbench AI now available