Geekbench AI Score

687
Single Precision Score
676
Half Precision Score
1384
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

User kszycho
Upload Date November 27 2025 09:02 PM
Views 10

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 16
Model samsung SM-A356B
Model IDsamsung SM-A356B
Motherboard s5e8835
Governorenergy_aware
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 2.00 GHz
Cluster 14 Cores @ 2.00 GHz
Cluster 24 Cores @ 2.40 GHz
Memory Information
Size 7.26 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 411
76.5 IPS
 
Image Classification (HP)
100% 376
69.9 IPS
 
Image Classification (Q)
100% 1224
227.6 IPS
 
Image Segmentation (SP)
100% 395
6.41 IPS
 
Image Segmentation (HP)
100% 381
6.17 IPS
 
Image Segmentation (Q)
98% 1158
18.8 IPS
 
Pose Estimation (SP)
100% 1526
1.78 IPS
 
Pose Estimation (HP)
100% 1499
1.75 IPS
 
Pose Estimation (Q)
84% 2506
2.97 IPS
 
Object Detection (SP)
100% 302
23.9 IPS
 
Object Detection (HP)
100% 304
24.1 IPS
 
Object Detection (Q)
83% 927
74.9 IPS
 
Face Detection (SP)
100% 876
10.4 IPS
 
Face Detection (HP)
100% 984
11.7 IPS
 
Face Detection (Q)
95% 2234
26.7 IPS
 
Depth Estimation (SP)
100% 1213
9.34 IPS
 
Depth Estimation (HP)
99% 1112
8.56 IPS
 
Depth Estimation (Q)
64% 2267
20.8 IPS
 
Style Transfer (SP)
89% 2553
3.31 IPS
 
Style Transfer (HP)
89% 2564
3.33 IPS
 
Style Transfer (Q)
98% 5832
7.52 IPS
 
Image Super-Resolution (SP)
100% 677
25.0 IPS
 
Image Super-Resolution (HP)
100% 669
24.7 IPS
 
Image Super-Resolution (Q)
97% 1385
51.3 IPS
 
Text Classification (SP)
100% 333
445.1 IPS
 
Text Classification (HP)
100% 328
437.7 IPS
 
Text Classification (Q)
88% 606
818.0 IPS
 
Machine Translation (SP)
100% 514
8.86 IPS
 
Machine Translation (HP)
100% 496
8.54 IPS
 
Machine Translation (Q)
50% 316
11.2 IPS
 

Compare

Set Baseline Geekbench 6 now available