Geekbench AI Score

541
Single Precision Score
540
Half Precision Score
1061
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

User M91
Upload Date August 08 2025 11:03 AM
Views 5

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% 241
44.8 IPS
 
Image Classification (HP)
100% 241
44.8 IPS
 
Image Classification (Q)
100% 728
135.4 IPS
 
Image Segmentation (SP)
100% 302
4.90 IPS
 
Image Segmentation (HP)
100% 310
5.03 IPS
 
Image Segmentation (Q)
98% 832
13.5 IPS
 
Pose Estimation (SP)
100% 1157
1.35 IPS
 
Pose Estimation (HP)
100% 1145
1.34 IPS
 
Pose Estimation (Q)
84% 1685
2.00 IPS
 
Object Detection (SP)
100% 234
18.6 IPS
 
Object Detection (HP)
100% 228
18.1 IPS
 
Object Detection (Q)
83% 717
57.9 IPS
 
Face Detection (SP)
100% 761
9.04 IPS
 
Face Detection (HP)
100% 751
8.93 IPS
 
Face Detection (Q)
95% 1722
20.6 IPS
 
Depth Estimation (SP)
100% 999
7.70 IPS
 
Depth Estimation (HP)
99% 996
7.68 IPS
 
Depth Estimation (Q)
64% 1635
15.0 IPS
 
Style Transfer (SP)
89% 1933
2.51 IPS
 
Style Transfer (HP)
89% 1958
2.54 IPS
 
Style Transfer (Q)
98% 3904
5.03 IPS
 
Image Super-Resolution (SP)
100% 524
19.3 IPS
 
Image Super-Resolution (HP)
100% 535
19.7 IPS
 
Image Super-Resolution (Q)
97% 1011
37.4 IPS
 
Text Classification (SP)
100% 294
392.2 IPS
 
Text Classification (HP)
100% 292
389.5 IPS
 
Text Classification (Q)
88% 597
804.7 IPS
 
Machine Translation (SP)
100% 482
8.29 IPS
 
Machine Translation (HP)
100% 476
8.19 IPS
 
Machine Translation (Q)
50% 374
13.3 IPS
 

Compare

Set Baseline Geekbench 6 now available