Geekbench AI Score

2205
Single Precision Score
2183
Half Precision Score
1427
Quantized Score
Geekbench AI 1.0.0 for Linux AVX2

Result Information

User laffer1
Upload Date August 15 2024 05:40 PM
Views 5

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Intel Core i9-11900K
System Information
Operating System Ubuntu 24.04 LTS
Model ASUS System Product Name
Motherboard ASUSTeK COMPUTER INC. PRIME Z590-P
CPU Information
Name Intel Core i9-11900K
Topology 1 Processor, 8 Cores, 16 Threads
Identifier GenuineIntel Family 6 Model 167 Stepping 1
Base Frequency 5.10 GHz
Cluster 10 Cores
Memory Information
Size 31.15 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1798
334.3 IPS
 
Image Classification (HP)
100% 1810
336.6 IPS
 
Image Classification (Q)
99% 973
181.5 IPS
 
Image Segmentation (SP)
100% 2115
34.3 IPS
 
Image Segmentation (HP)
100% 2101
34.1 IPS
 
Image Segmentation (Q)
98% 939
15.3 IPS
 
Pose Estimation (SP)
100% 2656
3.10 IPS
 
Pose Estimation (HP)
100% 2666
3.11 IPS
 
Pose Estimation (Q)
96% 2881
3.38 IPS
 
Object Detection (SP)
100% 1952
154.8 IPS
 
Object Detection (HP)
100% 1963
155.7 IPS
 
Object Detection (Q)
86% 910
73.2 IPS
 
Face Detection (SP)
100% 2672
31.8 IPS
 
Face Detection (HP)
100% 2430
28.9 IPS
 
Face Detection (Q)
97% 2375
28.3 IPS
 
Depth Estimation (SP)
100% 2433
18.7 IPS
 
Depth Estimation (HP)
100% 2362
18.2 IPS
 
Depth Estimation (Q)
74% 2069
16.8 IPS
 
Style Transfer (SP)
100% 2660
3.42 IPS
 
Style Transfer (HP)
100% 2667
3.43 IPS
 
Style Transfer (Q)
98% 4936
6.37 IPS
 
Image Super-Resolution (SP)
100% 1872
69.1 IPS
 
Image Super-Resolution (HP)
100% 1854
68.5 IPS
 
Image Super-Resolution (Q)
97% 1402
52.0 IPS
 
Text Classification (SP)
100% 1915
2.56 KIPS
 
Text Classification (HP)
100% 1936
2.58 KIPS
 
Text Classification (Q)
92% 721
969.1 IPS
 
Machine Translation (SP)
100% 2227
38.4 IPS
 
Machine Translation (HP)
100% 2252
38.8 IPS
 
Machine Translation (Q)
58% 597
14.0 IPS
 

Compare

Set Baseline Geekbench 6 now available