Geekbench AI Score

4036
Single Precision Score
6165
Half Precision Score
3013
Quantized Score
Geekbench AI 1.7.0 for Windows AVX2

Result Information

User kasid
Upload Date June 27 2026 06:25 AM
Views 8

System Information

AI Information
Framework ONNX
Backend DirectML
Device Intel(R) Arc(TM) Graphics
System Information
Operating System Microsoft Windows 10 Pro (64-bit)
Model ASUSTeK COMPUTER INC. ASUS EXPERTBOOK B3405CCA
Motherboard ASUSTeK COMPUTER INC. B3405CCA
Power PlanBalanced
CPU Information
Name Intel Core Ultra 5 125H
Topology 1 Processor, 14 Cores, 18 Threads
Identifier GenuineIntel Family 6 Model 170 Stepping 4
Base Frequency 3.60 GHz
Cluster 14 Cores
Cluster 210 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1897
352.8 IPS
 
Image Classification (HP)
100% 3360
624.9 IPS
 
Image Classification (Q)
100% 1633
303.6 IPS
 
Image Segmentation (SP)
100% 2703
43.8 IPS
 
Image Segmentation (HP)
100% 5960
96.6 IPS
 
Image Segmentation (Q)
98% 2251
36.6 IPS
 
Pose Estimation (SP)
100% 12153
14.2 IPS
 
Pose Estimation (HP)
100% 16183
18.9 IPS
 
Pose Estimation (Q)
95% 10577
12.4 IPS
 
Object Detection (SP)
100% 2162
171.5 IPS
 
Object Detection (HP)
99% 4078
324.4 IPS
 
Object Detection (Q)
86% 1825
146.7 IPS
 
Face Detection (SP)
100% 3894
46.3 IPS
 
Face Detection (HP)
100% 7332
87.1 IPS
 
Face Detection (Q)
97% 3090
36.9 IPS
 
Depth Estimation (SP)
100% 9011
69.4 IPS
 
Depth Estimation (HP)
98% 17413
134.6 IPS
 
Depth Estimation (Q)
76% 7022
56.3 IPS
 
Style Transfer (SP)
100% 38669
49.7 IPS
 
Style Transfer (HP)
100% 56857
73.1 IPS
 
Style Transfer (Q)
98% 27462
35.4 IPS
 
Image Super-Resolution (SP)
100% 5827
215.2 IPS
 
Image Super-Resolution (HP)
100% 9174
338.8 IPS
 
Image Super-Resolution (Q)
99% 3489
129.2 IPS
 
Text Classification (SP)
86% 587
793.6 IPS
 
Text Classification (HP)
99% 482
643.4 IPS
 
Text Classification (Q)
84% 447
607.2 IPS
 
Machine Translation (SP)
100% 1837
31.6 IPS
 
Machine Translation (HP)
100% 1872
32.2 IPS
 
Machine Translation (Q)
70% 936
17.6 IPS
 

Compare

Set Baseline Geekbench AI now available