Geekbench AI Score

925
Single Precision Score
922
Half Precision Score
1951
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

Upload Date December 09 2025 11:30 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 16
Model samsung SM-A366B
Model IDsamsung SM-A366B
Motherboard parrot
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 2
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.40 GHz
Memory Information
Size 5.25 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 456
84.8 IPS
 
Image Classification (HP)
100% 449
83.5 IPS
 
Image Classification (Q)
100% 1445
268.8 IPS
 
Image Segmentation (SP)
100% 536
8.68 IPS
 
Image Segmentation (HP)
100% 539
8.74 IPS
 
Image Segmentation (Q)
98% 1654
26.9 IPS
 
Pose Estimation (SP)
100% 2023
2.36 IPS
 
Pose Estimation (HP)
100% 2005
2.34 IPS
 
Pose Estimation (Q)
84% 3771
4.47 IPS
 
Object Detection (SP)
100% 455
36.1 IPS
 
Object Detection (HP)
100% 457
36.3 IPS
 
Object Detection (Q)
83% 1284
103.7 IPS
 
Face Detection (SP)
100% 1143
13.6 IPS
 
Face Detection (HP)
100% 1146
13.6 IPS
 
Face Detection (Q)
95% 3400
40.6 IPS
 
Depth Estimation (SP)
100% 1572
12.1 IPS
 
Depth Estimation (HP)
99% 1597
12.3 IPS
 
Depth Estimation (Q)
64% 3412
31.3 IPS
 
Style Transfer (SP)
89% 3704
4.81 IPS
 
Style Transfer (HP)
89% 3659
4.75 IPS
 
Style Transfer (Q)
98% 8204
10.6 IPS
 
Image Super-Resolution (SP)
100% 852
31.5 IPS
 
Image Super-Resolution (HP)
100% 858
31.7 IPS
 
Image Super-Resolution (Q)
97% 1853
68.6 IPS
 
Text Classification (SP)
100% 493
657.7 IPS
 
Text Classification (HP)
100% 488
651.8 IPS
 
Text Classification (Q)
88% 922
1.24 KIPS
 
Machine Translation (SP)
100% 733
12.6 IPS
 
Machine Translation (HP)
100% 715
12.3 IPS
 
Machine Translation (Q)
50% 426
15.1 IPS
 

Compare

Set Baseline Geekbench 6 now available