Geekbench AI Score

210
Single Precision Score
211
Half Precision Score
524
Quantized Score
Geekbench AI 1.7.0 for Android AArch64

Result Information

User aaron762
Upload Date March 25 2026 06:13 AM
Views 15

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device Qualcomm Snapdragon 8 Gen 1
System Information
Operating System Android 16
Model Samsung Galaxy S22 Ultra
Model IDsamsung SM-S908U1
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 10.94 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 122
22.6 IPS
 
Image Classification (HP)
100% 122
22.7 IPS
 
Image Classification (Q)
99% 340
63.5 IPS
 
Image Segmentation (SP)
100% 157
2.55 IPS
 
Image Segmentation (HP)
100% 158
2.57 IPS
 
Image Segmentation (Q)
98% 390
6.34 IPS
 
Pose Estimation (SP)
100% 217
0.25 IPS
 
Pose Estimation (HP)
100% 218
0.25 IPS
 
Pose Estimation (Q)
98% 882
1.03 IPS
 
Object Detection (SP)
100% 122
9.64 IPS
 
Object Detection (HP)
100% 122
9.65 IPS
 
Object Detection (Q)
87% 370
29.7 IPS
 
Face Detection (SP)
100% 348
4.13 IPS
 
Face Detection (HP)
100% 354
4.21 IPS
 
Face Detection (Q)
97% 830
9.90 IPS
 
Depth Estimation (SP)
100% 280
2.16 IPS
 
Depth Estimation (HP)
99% 267
2.06 IPS
 
Depth Estimation (Q)
64% 689
6.25 IPS
 
Style Transfer (SP)
100% 489
0.63 IPS
 
Style Transfer (HP)
100% 491
0.63 IPS
 
Style Transfer (Q)
98% 1269
1.64 IPS
 
Image Super-Resolution (SP)
100% 133
4.92 IPS
 
Image Super-Resolution (HP)
100% 132
4.89 IPS
 
Image Super-Resolution (Q)
97% 506
18.7 IPS
 
Text Classification (SP)
100% 174
232.3 IPS
 
Text Classification (HP)
100% 173
230.9 IPS
 
Text Classification (Q)
91% 320
429.7 IPS
 
Machine Translation (SP)
100% 301
5.19 IPS
 
Machine Translation (HP)
100% 333
5.73 IPS
 
Machine Translation (Q)
57% 307
7.50 IPS
 

Compare

Set Baseline Geekbench AI now available