Geekbench AI Score

547
Single Precision Score
546
Half Precision Score
1067
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

User M91
Upload Date July 24 2025 01:00 PM
Views 8

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 15
Model samsung SM-X210
Model IDsamsung SM-X210
Motherboard holi
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.21 GHz
Memory Information
Size 7.21 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 240
44.7 IPS
 
Image Classification (HP)
100% 241
44.8 IPS
 
Image Classification (Q)
100% 726
135.0 IPS
 
Image Segmentation (SP)
100% 315
5.11 IPS
 
Image Segmentation (HP)
100% 315
5.11 IPS
 
Image Segmentation (Q)
98% 828
13.5 IPS
 
Pose Estimation (SP)
100% 1171
1.37 IPS
 
Pose Estimation (HP)
100% 1161
1.35 IPS
 
Pose Estimation (Q)
84% 1744
2.07 IPS
 
Object Detection (SP)
100% 229
18.2 IPS
 
Object Detection (HP)
100% 234
18.6 IPS
 
Object Detection (Q)
83% 715
57.7 IPS
 
Face Detection (SP)
100% 778
9.25 IPS
 
Face Detection (HP)
100% 776
9.22 IPS
 
Face Detection (Q)
95% 1716
20.5 IPS
 
Depth Estimation (SP)
100% 1013
7.80 IPS
 
Depth Estimation (HP)
99% 1014
7.81 IPS
 
Depth Estimation (Q)
64% 1620
14.8 IPS
 
Style Transfer (SP)
89% 1987
2.58 IPS
 
Style Transfer (HP)
89% 1947
2.53 IPS
 
Style Transfer (Q)
98% 4041
5.21 IPS
 
Image Super-Resolution (SP)
100% 532
19.7 IPS
 
Image Super-Resolution (HP)
100% 539
19.9 IPS
 
Image Super-Resolution (Q)
97% 1011
37.5 IPS
 
Text Classification (SP)
100% 291
388.8 IPS
 
Text Classification (HP)
100% 289
386.1 IPS
 
Text Classification (Q)
88% 590
796.3 IPS
 
Machine Translation (SP)
100% 488
8.41 IPS
 
Machine Translation (HP)
100% 480
8.28 IPS
 
Machine Translation (Q)
50% 382
13.6 IPS
 

Compare

Set Baseline Geekbench 6 now available