Geekbench AI Score

223
Single Precision Score
19086
Half Precision Score
40577
Quantized Score
Geekbench AI 1.8.0 for Android AArch64

Result Information

Upload Date November 20 2026 08:36 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm Snapdragon 8 Gen 2
System Information
Operating System Android 17
Model Samsung Galaxy S23 Ultra
Model IDsamsung SM-S918B
Motherboard kalama
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3406 revision 0
Base Frequency 2.02 GHz
Cluster 13 Cores @ 2.02 GHz
Cluster 24 Cores @ 2.80 GHz
Cluster 31 Core @ 3.36 GHz
Memory Information
Size 10.79 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 127
23.7 IPS
 
Image Classification (HP)
100% 12680
2.36 KIPS
 
Image Classification (Q)
96% 30812
5.75 KIPS
 
Image Segmentation (SP)
100% 168
2.72 IPS
 
Image Segmentation (HP)
100% 7437
120.6 IPS
 
Image Segmentation (Q)
98% 27064
440.1 IPS
 
Pose Estimation (SP)
100% 229
0.27 IPS
 
Pose Estimation (HP)
100% 73448
85.7 IPS
 
Pose Estimation (Q)
98% 292610
342.5 IPS
 
Object Detection (SP)
100% 126
10.0 IPS
 
Object Detection (HP)
100% 12368
981.1 IPS
 
Object Detection (Q)
86% 17219
1.38 KIPS
 
Face Detection (SP)
100% 364
4.32 IPS
 
Face Detection (HP)
100% 25375
301.5 IPS
 
Face Detection (Q)
97% 75887
905.0 IPS
 
Depth Estimation (SP)
100% 307
2.37 IPS
 
Depth Estimation (HP)
99% 49330
380.1 IPS
 
Depth Estimation (Q)
63% 103223
972.3 IPS
 
Style Transfer (SP)
100% 546
0.70 IPS
 
Style Transfer (HP)
100% 91539
117.7 IPS
 
Style Transfer (Q)
98% 287744
371.0 IPS
 
Image Super-Resolution (SP)
100% 146
5.38 IPS
 
Image Super-Resolution (HP)
100% 34420
1.27 KIPS
 
Image Super-Resolution (Q)
97% 82528
3.06 KIPS
 
Text Classification (SP)
100% 175
233.3 IPS
 
Text Classification (HP)
100% 5141
6.86 KIPS
 
Text Classification (Q)
93% 7953
10.7 KIPS
 
Machine Translation (SP)
100% 326
5.62 IPS
 
Machine Translation (HP)
100% 3694
63.6 IPS
 
Machine Translation (Q)
55% 1947
51.0 IPS
 

Compare

Set Baseline Geekbench AI now available