Geekbench AI Score

569
Single Precision Score
340
Half Precision Score
622
Quantized Score
Geekbench AI 1.3.0 for Windows x86 (64-bit)

Result Information

User KjellinJ
Upload Date June 28 2025 08:13 PM
Views 9

System Information

AI Information
Framework ONNX
Backend CPU
Device Intel Core i7-2860QM
System Information
Operating System Microsoft Windows 10 Pro (64-bit)
Model Hewlett-Packard HP ProBook 6560b
Motherboard Hewlett-Packard 1619
Power PlanBalanserat
CPU Information
Name Intel Core i7-2860QM
Topology 1 Processor, 4 Cores, 8 Threads
Identifier GenuineIntel Family 6 Model 42 Stepping 7
Base Frequency 2.50 GHz
Cluster 14 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 397
73.9 IPS
 
Image Classification (HP)
100% 153
28.5 IPS
 
Image Classification (Q)
96% 452
84.4 IPS
 
Image Segmentation (SP)
100% 243
3.94 IPS
 
Image Segmentation (HP)
100% 201
3.26 IPS
 
Image Segmentation (Q)
97% 372
6.06 IPS
 
Pose Estimation (SP)
100% 660
0.77 IPS
 
Pose Estimation (HP)
100% 624
0.73 IPS
 
Pose Estimation (Q)
86% 924
1.09 IPS
 
Object Detection (SP)
100% 390
30.9 IPS
 
Object Detection (HP)
100% 176
13.9 IPS
 
Object Detection (Q)
58% 358
39.1 IPS
 
Face Detection (SP)
100% 988
11.7 IPS
 
Face Detection (HP)
100% 456
5.42 IPS
 
Face Detection (Q)
96% 1080
12.9 IPS
 
Depth Estimation (SP)
100% 983
7.57 IPS
 
Depth Estimation (HP)
99% 514
3.96 IPS
 
Depth Estimation (Q)
78% 1088
8.66 IPS
 
Style Transfer (SP)
100% 1968
2.53 IPS
 
Style Transfer (HP)
100% 1639
2.11 IPS
 
Style Transfer (Q)
87% 2032
2.64 IPS
 
Image Super-Resolution (SP)
100% 393
14.5 IPS
 
Image Super-Resolution (HP)
100% 348
12.8 IPS
 
Image Super-Resolution (Q)
97% 512
19.0 IPS
 
Text Classification (SP)
100% 376
502.3 IPS
 
Text Classification (HP)
100% 208
277.5 IPS
 
Text Classification (Q)
97% 199
266.6 IPS
 
Machine Translation (SP)
100% 515
8.86 IPS
 
Machine Translation (HP)
100% 226
3.89 IPS
 
Machine Translation (Q)
68% 648
12.5 IPS
 

Compare

Set Baseline Geekbench 6 now available