Geekbench AI Score

865
Single Precision Score
728
Half Precision Score
757
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date June 14 2025 08:07 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device Samsung Exynos 2200
System Information
Operating System Android 15
Model Samsung Galaxy S22+
Model IDsamsung SM-S906B
Motherboard s5e9925
Governorenergy_aware
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 1.82 GHz
Cluster 14 Cores @ 1.82 GHz
Cluster 23 Cores @ 2.52 GHz
Cluster 31 Core @ 2.80 GHz
Memory Information
Size 7.10 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 347
64.6 IPS
 
Image Classification (HP)
100% 251
46.7 IPS
 
Image Classification (Q)
99% 237
44.1 IPS
 
Image Segmentation (SP)
100% 524
8.50 IPS
 
Image Segmentation (HP)
100% 994
16.1 IPS
 
Image Segmentation (Q)
98% 1000
16.3 IPS
 
Pose Estimation (SP)
100% 1747
2.04 IPS
 
Pose Estimation (HP)
100% 1050
1.23 IPS
 
Pose Estimation (Q)
96% 1030
1.21 IPS
 
Object Detection (SP)
100% 462
36.7 IPS
 
Object Detection (HP)
100% 335
26.5 IPS
 
Object Detection (Q)
86% 405
32.5 IPS
 
Face Detection (SP)
100% 2224
26.4 IPS
 
Face Detection (HP)
100% 1784
21.2 IPS
 
Face Detection (Q)
97% 1593
19.0 IPS
 
Depth Estimation (SP)
100% 1974
15.2 IPS
 
Depth Estimation (HP)
99% 1337
10.3 IPS
 
Depth Estimation (Q)
63% 1092
10.2 IPS
 
Style Transfer (SP)
100% 5109
6.57 IPS
 
Style Transfer (HP)
100% 3271
4.20 IPS
 
Style Transfer (Q)
98% 3277
4.23 IPS
 
Image Super-Resolution (SP)
100% 820
30.3 IPS
 
Image Super-Resolution (HP)
100% 690
25.5 IPS
 
Image Super-Resolution (Q)
97% 657
24.3 IPS
 
Text Classification (SP)
100% 230
307.6 IPS
 
Text Classification (HP)
100% 236
314.8 IPS
 
Text Classification (Q)
91% 467
627.1 IPS
 
Machine Translation (SP)
100% 380
6.55 IPS
 
Machine Translation (HP)
100% 376
6.47 IPS
 
Machine Translation (Q)
57% 360
8.79 IPS
 

Compare

Set Baseline Geekbench 6 now available