Geekbench AI Score

537
Single Precision Score
540
Half Precision Score
1053
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

User M91
Upload Date August 27 2025 02:05 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
44.6 IPS
 
Image Classification (HP)
100% 236
43.9 IPS
 
Image Classification (Q)
100% 728
135.4 IPS
 
Image Segmentation (SP)
100% 302
4.89 IPS
 
Image Segmentation (HP)
100% 312
5.05 IPS
 
Image Segmentation (Q)
98% 832
13.5 IPS
 
Pose Estimation (SP)
100% 1156
1.35 IPS
 
Pose Estimation (HP)
100% 1143
1.33 IPS
 
Pose Estimation (Q)
84% 1653
1.96 IPS
 
Object Detection (SP)
100% 233
18.5 IPS
 
Object Detection (HP)
100% 234
18.6 IPS
 
Object Detection (Q)
83% 718
58.0 IPS
 
Face Detection (SP)
100% 745
8.86 IPS
 
Face Detection (HP)
100% 768
9.12 IPS
 
Face Detection (Q)
95% 1646
19.6 IPS
 
Depth Estimation (SP)
100% 989
7.62 IPS
 
Depth Estimation (HP)
99% 989
7.62 IPS
 
Depth Estimation (Q)
64% 1590
14.6 IPS
 
Style Transfer (SP)
89% 1944
2.52 IPS
 
Style Transfer (HP)
89% 1973
2.56 IPS
 
Style Transfer (Q)
98% 3889
5.02 IPS
 
Image Super-Resolution (SP)
100% 522
19.3 IPS
 
Image Super-Resolution (HP)
100% 529
19.5 IPS
 
Image Super-Resolution (Q)
97% 1011
37.5 IPS
 
Text Classification (SP)
100% 294
392.7 IPS
 
Text Classification (HP)
100% 290
387.7 IPS
 
Text Classification (Q)
88% 594
801.3 IPS
 
Machine Translation (SP)
100% 471
8.12 IPS
 
Machine Translation (HP)
100% 472
8.14 IPS
 
Machine Translation (Q)
50% 384
13.6 IPS
 

Compare

Set Baseline Geekbench 6 now available