Geekbench AI Score

535
Single Precision Score
941
Half Precision Score
749
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

User M91
Upload Date November 08 2025 02:46 AM
Views 4

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% 408
75.9 IPS
 
Image Classification (HP)
100% 683
127.0 IPS
 
Image Classification (Q)
100% 650
120.9 IPS
 
Image Segmentation (SP)
100% 584
9.47 IPS
 
Image Segmentation (HP)
100% 1052
17.1 IPS
 
Image Segmentation (Q)
98% 994
16.2 IPS
 
Pose Estimation (SP)
100% 1978
2.31 IPS
 
Pose Estimation (HP)
99% 3833
4.49 IPS
 
Pose Estimation (Q)
96% 3823
4.48 IPS
 
Object Detection (SP)
100% 355
28.1 IPS
 
Object Detection (HP)
99% 593
47.1 IPS
 
Object Detection (Q)
87% 567
45.5 IPS
 
Face Detection (SP)
100% 1043
12.4 IPS
 
Face Detection (HP)
100% 2039
24.2 IPS
 
Face Detection (Q)
97% 1790
21.3 IPS
 
Depth Estimation (SP)
100% 1179
9.08 IPS
 
Depth Estimation (HP)
98% 2336
18.1 IPS
 
Depth Estimation (Q)
61% 1737
17.1 IPS
 
Style Transfer (SP)
100% 2098
2.70 IPS
 
Style Transfer (HP)
100% 4528
5.82 IPS
 
Style Transfer (Q)
98% 4507
5.81 IPS
 
Image Super-Resolution (SP)
100% 515
19.0 IPS
 
Image Super-Resolution (HP)
100% 1032
38.1 IPS
 
Image Super-Resolution (Q)
97% 987
36.6 IPS
 
Text Classification (SP)
35% 23
219.2 IPS
 
Text Classification (HP)
35% 35
317.2 IPS
 
Text Classification (Q)
33% 26
311.8 IPS
 
Machine Translation (SP)
100% 380
6.55 IPS
 
Machine Translation (HP)
97% 432
7.46 IPS
 
Machine Translation (Q)
43% 111
6.34 IPS
 

Compare

Set Baseline Geekbench 6 now available