Geekbench AI Score

1541
Single Precision Score
1540
Half Precision Score
2269
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date May 08 2025 01:18 AM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Qualcomm Snapdragon 8 Gen 1
System Information
Operating System Android 15
Model Samsung Galaxy S22
Model IDsamsung SM-S901N
Motherboard taro
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.50 GHz
Cluster 31 Core @ 3.00 GHz
Memory Information
Size 7.05 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1155
214.8 IPS
 
Image Classification (HP)
100% 1312
244.1 IPS
 
Image Classification (Q)
100% 1879
349.5 IPS
 
Image Segmentation (SP)
100% 1372
22.2 IPS
 
Image Segmentation (HP)
100% 1370
22.2 IPS
 
Image Segmentation (Q)
98% 2067
33.6 IPS
 
Pose Estimation (SP)
100% 2299
2.68 IPS
 
Pose Estimation (HP)
100% 2239
2.61 IPS
 
Pose Estimation (Q)
84% 4725
5.60 IPS
 
Object Detection (SP)
98% 1225
97.5 IPS
 
Object Detection (HP)
98% 1231
98.0 IPS
 
Object Detection (Q)
83% 1748
141.2 IPS
 
Face Detection (SP)
100% 2390
28.4 IPS
 
Face Detection (HP)
100% 2299
27.3 IPS
 
Face Detection (Q)
95% 3792
45.3 IPS
 
Depth Estimation (SP)
99% 2496
19.3 IPS
 
Depth Estimation (HP)
99% 2529
19.5 IPS
 
Depth Estimation (Q)
64% 3759
34.4 IPS
 
Style Transfer (SP)
89% 4841
6.28 IPS
 
Style Transfer (HP)
89% 4659
6.05 IPS
 
Style Transfer (Q)
98% 8726
11.3 IPS
 
Image Super-Resolution (SP)
100% 1106
40.8 IPS
 
Image Super-Resolution (HP)
100% 1107
40.9 IPS
 
Image Super-Resolution (Q)
97% 2181
80.8 IPS
 
Text Classification (SP)
100% 449
599.5 IPS
 
Text Classification (HP)
99% 450
600.3 IPS
 
Text Classification (Q)
88% 798
1.08 KIPS
 
Machine Translation (SP)
100% 1183
20.4 IPS
 
Machine Translation (HP)
100% 1125
19.4 IPS
 
Machine Translation (Q)
50% 522
18.5 IPS
 

Compare

Set Baseline Geekbench 6 now available