Geekbench AI Score

2289
Single Precision Score
1067
Half Precision Score
3228
Quantized Score
Geekbench AI 1.3.0 for Windows AVX2

Result Information

User punkouter25
Upload Date May 05 2025 11:10 PM
Views 9

System Information

AI Information
Framework ONNX
Backend CPU
Device Intel Core i7-10750H
System Information
Operating System Microsoft Windows 11 Pro N (64-bit)
Model LENOVO 81Y8
Motherboard LENOVO LNVNB161216
Power PlanBalanced
CPU Information
Name Intel Core i7-10750H
Topology 1 Processor, 6 Cores, 12 Threads
Identifier GenuineIntel Family 6 Model 165 Stepping 2
Base Frequency 2.59 GHz
Cluster 16 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1806
335.8 IPS
 
Image Classification (HP)
100% 415
77.2 IPS
 
Image Classification (Q)
96% 2941
549.1 IPS
 
Image Segmentation (SP)
100% 1016
16.5 IPS
 
Image Segmentation (HP)
100% 601
9.74 IPS
 
Image Segmentation (Q)
97% 1787
29.1 IPS
 
Pose Estimation (SP)
100% 3505
4.09 IPS
 
Pose Estimation (HP)
100% 2815
3.28 IPS
 
Pose Estimation (Q)
86% 6924
8.19 IPS
 
Object Detection (SP)
100% 1766
140.1 IPS
 
Object Detection (HP)
100% 519
41.1 IPS
 
Object Detection (Q)
58% 2108
230.3 IPS
 
Face Detection (SP)
100% 2908
34.6 IPS
 
Face Detection (HP)
100% 1037
12.3 IPS
 
Face Detection (Q)
96% 5016
59.8 IPS
 
Depth Estimation (SP)
100% 4667
36.0 IPS
 
Depth Estimation (HP)
99% 1518
11.7 IPS
 
Depth Estimation (Q)
78% 6204
49.5 IPS
 
Style Transfer (SP)
100% 8461
10.9 IPS
 
Style Transfer (HP)
100% 6796
8.74 IPS
 
Style Transfer (Q)
87% 11201
14.6 IPS
 
Image Super-Resolution (SP)
100% 1550
57.2 IPS
 
Image Super-Resolution (HP)
100% 1413
52.2 IPS
 
Image Super-Resolution (Q)
97% 2189
81.1 IPS
 
Text Classification (SP)
100% 1217
1.62 KIPS
 
Text Classification (HP)
100% 631
842.7 IPS
 
Text Classification (Q)
97% 1069
1.43 KIPS
 
Machine Translation (SP)
100% 1612
27.8 IPS
 
Machine Translation (HP)
100% 553
9.52 IPS
 
Machine Translation (Q)
68% 1969
38.1 IPS
 

Compare

Set Baseline Geekbench 6 now available