Geekbench AI Score

541
Single Precision Score
540
Half Precision Score
1040
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

User M91
Upload Date August 28 2025 01:48 AM
Views 4

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% 238
44.3 IPS
 
Image Classification (Q)
100% 731
135.9 IPS
 
Image Segmentation (SP)
100% 301
4.88 IPS
 
Image Segmentation (HP)
100% 314
5.09 IPS
 
Image Segmentation (Q)
98% 832
13.5 IPS
 
Pose Estimation (SP)
100% 1146
1.34 IPS
 
Pose Estimation (HP)
100% 1143
1.33 IPS
 
Pose Estimation (Q)
84% 1641
1.95 IPS
 
Object Detection (SP)
100% 231
18.4 IPS
 
Object Detection (HP)
100% 232
18.4 IPS
 
Object Detection (Q)
83% 707
57.1 IPS
 
Face Detection (SP)
100% 769
9.14 IPS
 
Face Detection (HP)
100% 752
8.94 IPS
 
Face Detection (Q)
95% 1624
19.4 IPS
 
Depth Estimation (SP)
100% 1017
7.84 IPS
 
Depth Estimation (HP)
99% 996
7.67 IPS
 
Depth Estimation (Q)
64% 1531
14.0 IPS
 
Style Transfer (SP)
89% 1989
2.58 IPS
 
Style Transfer (HP)
89% 1984
2.58 IPS
 
Style Transfer (Q)
98% 3910
5.04 IPS
 
Image Super-Resolution (SP)
100% 523
19.3 IPS
 
Image Super-Resolution (HP)
100% 528
19.5 IPS
 
Image Super-Resolution (Q)
97% 997
36.9 IPS
 
Text Classification (SP)
100% 292
390.4 IPS
 
Text Classification (HP)
100% 293
390.8 IPS
 
Text Classification (Q)
88% 598
806.1 IPS
 
Machine Translation (SP)
100% 477
8.22 IPS
 
Machine Translation (HP)
100% 468
8.06 IPS
 
Machine Translation (Q)
50% 364
12.9 IPS
 

Compare

Set Baseline Geekbench 6 now available