Geekbench AI Score

1425
Single Precision Score
2129
Half Precision Score
2026
Quantized Score
Geekbench AI 1.6.0 for Windows AVX2

Result Information

User Trinity33R
Upload Date February 01 2026 04:36 AM
Views 17

System Information

AI Information
Framework OpenVINO
Backend GPU
Device Intel(R) UHD Graphics 630 (iGPU)
System Information
Operating System Microsoft Windows 10 Pro (64-bit)
Model LENOVO 20MFCTO1WW
Motherboard LENOVO 20MFCTO1WW
CPU Information
Name Intel Core i7-8750H
Topology 1 Processor, 6 Cores, 12 Threads
Identifier GenuineIntel Family 6 Model 158 Stepping 10
Base Frequency 2.21 GHz
Cluster 16 Cores
Memory Information
Size 32.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 958
178.1 IPS
 
Image Classification (HP)
100% 1513
281.3 IPS
 
Image Classification (Q)
100% 1382
256.9 IPS
 
Image Segmentation (SP)
100% 1155
18.7 IPS
 
Image Segmentation (HP)
100% 1865
30.2 IPS
 
Image Segmentation (Q)
99% 1776
28.9 IPS
 
Pose Estimation (SP)
100% 2071
2.42 IPS
 
Pose Estimation (HP)
99% 1995
2.33 IPS
 
Pose Estimation (Q)
97% 3063
3.59 IPS
 
Object Detection (SP)
100% 817
64.8 IPS
 
Object Detection (HP)
99% 1444
114.9 IPS
 
Object Detection (Q)
88% 1396
112.0 IPS
 
Face Detection (SP)
100% 2587
30.7 IPS
 
Face Detection (HP)
100% 4336
51.5 IPS
 
Face Detection (Q)
97% 3620
43.2 IPS
 
Depth Estimation (SP)
100% 2387
18.4 IPS
 
Depth Estimation (HP)
98% 4545
35.1 IPS
 
Depth Estimation (Q)
89% 3993
31.1 IPS
 
Style Transfer (SP)
100% 6173
7.94 IPS
 
Style Transfer (HP)
100% 8316
10.7 IPS
 
Style Transfer (Q)
98% 7632
9.84 IPS
 
Image Super-Resolution (SP)
100% 1058
39.1 IPS
 
Image Super-Resolution (HP)
100% 1840
67.9 IPS
 
Image Super-Resolution (Q)
99% 1800
66.7 IPS
 
Text Classification (SP)
71% 588
850.8 IPS
 
Text Classification (HP)
71% 774
1.12 KIPS
 
Text Classification (Q)
92% 557
748.2 IPS
 
Machine Translation (SP)
100% 781
13.4 IPS
 
Machine Translation (HP)
99% 1009
17.4 IPS
 
Machine Translation (Q)
98% 1007
17.4 IPS
 

Compare

Set Baseline Geekbench 6 now available