Geekbench AI Score

537
Single Precision Score
942
Half Precision Score
746
Quantized Score
Geekbench AI 1.6.1 for Android AArch64

Result Information

User M91
Upload Date January 10 2026 12:00 PM
Views 10

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM ARMv8
System Information
Operating System Android 16
Model samsung SM-A366W
Model IDsamsung SM-A366W
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% 404
75.0 IPS
 
Image Classification (HP)
100% 691
128.4 IPS
 
Image Classification (Q)
100% 661
122.9 IPS
 
Image Segmentation (SP)
100% 595
9.64 IPS
 
Image Segmentation (HP)
100% 1016
16.5 IPS
 
Image Segmentation (Q)
98% 966
15.7 IPS
 
Pose Estimation (SP)
100% 1971
2.30 IPS
 
Pose Estimation (HP)
99% 3817
4.47 IPS
 
Pose Estimation (Q)
96% 3776
4.42 IPS
 
Object Detection (SP)
100% 357
28.3 IPS
 
Object Detection (HP)
99% 606
48.0 IPS
 
Object Detection (Q)
87% 562
45.2 IPS
 
Face Detection (SP)
100% 1042
12.4 IPS
 
Face Detection (HP)
100% 2071
24.6 IPS
 
Face Detection (Q)
97% 1788
21.3 IPS
 
Depth Estimation (SP)
100% 1183
9.12 IPS
 
Depth Estimation (HP)
98% 2315
17.9 IPS
 
Depth Estimation (Q)
61% 1725
17.0 IPS
 
Style Transfer (SP)
100% 2169
2.79 IPS
 
Style Transfer (HP)
100% 4557
5.86 IPS
 
Style Transfer (Q)
98% 4536
5.85 IPS
 
Image Super-Resolution (SP)
100% 540
19.9 IPS
 
Image Super-Resolution (HP)
100% 1036
38.3 IPS
 
Image Super-Resolution (Q)
97% 999
37.0 IPS
 
Text Classification (SP)
35% 22
216.3 IPS
 
Text Classification (HP)
35% 35
315.4 IPS
 
Text Classification (Q)
33% 26
312.1 IPS
 
Machine Translation (SP)
100% 372
6.40 IPS
 
Machine Translation (HP)
97% 430
7.43 IPS
 
Machine Translation (Q)
43% 109
6.17 IPS
 

Compare

Set Baseline Geekbench 6 now available