Geekbench AI Score

1813
Single Precision Score
4329
Half Precision Score
1417
Quantized Score
Geekbench AI 1.0.0 for Windows AVX2

Result Information

Upload Date September 17 2024 01:27 PM
Views 1

System Information

AI Information
Framework ONNX
Backend DirectML
Device Intel(R) Graphics
System Information
Operating System Microsoft Windows 11 Enterprise (64-bit)
Model HP HP EliteBook 640 14 inch G11 Notebook PC
Motherboard HP 8C86
Power PlanBalanced
CPU Information
Name Intel(R) Core(TM) Ultra 5 135U
Topology 1 Processor, 12 Cores, 14 Threads
Identifier GenuineIntel Family 6 Model 170 Stepping 4
Base Frequency 1.60 GHz
Cluster 12 Cores
Cluster 210 Cores
Memory Information
Size 32.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 627
116.5 IPS
 
Image Classification (HP)
100% 2883
536.2 IPS
 
Image Classification (Q)
100% 575
106.9 IPS
 
Image Segmentation (SP)
100% 785
12.7 IPS
 
Image Segmentation (HP)
100% 4607
74.7 IPS
 
Image Segmentation (Q)
98% 707
11.5 IPS
 
Pose Estimation (SP)
100% 7116
8.30 IPS
 
Pose Estimation (HP)
100% 10916
12.7 IPS
 
Pose Estimation (Q)
97% 6355
7.44 IPS
 
Object Detection (SP)
100% 621
49.3 IPS
 
Object Detection (HP)
99% 2816
224.0 IPS
 
Object Detection (Q)
89% 534
42.7 IPS
 
Face Detection (SP)
100% 925
11.0 IPS
 
Face Detection (HP)
100% 4631
55.0 IPS
 
Face Detection (Q)
97% 813
9.70 IPS
 
Depth Estimation (SP)
100% 3672
28.3 IPS
 
Depth Estimation (HP)
99% 12400
95.8 IPS
 
Depth Estimation (Q)
73% 3035
24.8 IPS
 
Style Transfer (SP)
100% 21203
27.3 IPS
 
Style Transfer (HP)
100% 31920
41.0 IPS
 
Style Transfer (Q)
98% 17172
22.1 IPS
 
Image Super-Resolution (SP)
100% 3497
129.1 IPS
 
Image Super-Resolution (HP)
100% 5075
187.4 IPS
 
Image Super-Resolution (Q)
99% 2595
96.1 IPS
 
Text Classification (SP)
86% 704
952.1 IPS
 
Text Classification (HP)
99% 642
857.2 IPS
 
Text Classification (Q)
83% 488
664.8 IPS
 
Machine Translation (SP)
100% 999
17.2 IPS
 
Machine Translation (HP)
100% 948
16.3 IPS
 
Machine Translation (Q)
60% 441
9.84 IPS
 

Compare

Set Baseline Geekbench 6 now available