Geekbench AI Score

525
Single Precision Score
517
Half Precision Score
996
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User 2048
Upload Date June 30 2025 09:54 AM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model samsung SM-A236U
Model IDsamsung SM-A236U
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 3.38 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 233
43.4 IPS
 
Image Classification (HP)
100% 235
43.7 IPS
 
Image Classification (Q)
100% 712
132.5 IPS
 
Image Segmentation (SP)
100% 307
4.98 IPS
 
Image Segmentation (HP)
100% 306
4.96 IPS
 
Image Segmentation (Q)
98% 820
13.3 IPS
 
Pose Estimation (SP)
100% 1167
1.36 IPS
 
Pose Estimation (HP)
100% 1171
1.37 IPS
 
Pose Estimation (Q)
84% 1732
2.05 IPS
 
Object Detection (SP)
100% 238
18.9 IPS
 
Object Detection (HP)
100% 238
18.9 IPS
 
Object Detection (Q)
83% 708
57.2 IPS
 
Face Detection (SP)
100% 755
8.97 IPS
 
Face Detection (HP)
100% 754
8.95 IPS
 
Face Detection (Q)
95% 1706
20.4 IPS
 
Depth Estimation (SP)
100% 1000
7.71 IPS
 
Depth Estimation (HP)
99% 998
7.69 IPS
 
Depth Estimation (Q)
64% 1601
14.7 IPS
 
Style Transfer (SP)
89% 2004
2.60 IPS
 
Style Transfer (HP)
89% 2004
2.60 IPS
 
Style Transfer (Q)
98% 3908
5.04 IPS
 
Image Super-Resolution (SP)
100% 525
19.4 IPS
 
Image Super-Resolution (HP)
100% 505
18.7 IPS
 
Image Super-Resolution (Q)
97% 868
32.1 IPS
 
Text Classification (SP)
100% 250
333.4 IPS
 
Text Classification (HP)
100% 237
316.0 IPS
 
Text Classification (Q)
88% 473
637.5 IPS
 
Machine Translation (SP)
100% 408
7.04 IPS
 
Machine Translation (HP)
100% 381
6.57 IPS
 
Machine Translation (Q)
50% 309
11.0 IPS
 

Compare

Set Baseline Geekbench 6 now available