Geekbench AI Score

396
Single Precision Score
17252
Half Precision Score
42378
Quantized Score
Geekbench AI 1.6.0 Corporate for Android AArch64

Result Information

Upload Date December 02 2025 06:16 PM
Views 6

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm Snapdragon 8 Gen 2
System Information
Operating System Android 16
Model Samsung Galaxy S23
Model IDsamsung SM-S911W
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 6.91 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 238
44.3 IPS
 
Image Classification (HP)
100% 13331
2.48 KIPS
 
Image Classification (Q)
96% 31671
5.91 KIPS
 
Image Segmentation (SP)
100% 311
5.04 IPS
 
Image Segmentation (HP)
100% 7898
128.0 IPS
 
Image Segmentation (Q)
98% 27993
455.2 IPS
 
Pose Estimation (SP)
100% 433
0.51 IPS
 
Pose Estimation (HP)
100% 72348
84.4 IPS
 
Pose Estimation (Q)
98% 293677
343.7 IPS
 
Object Detection (SP)
100% 234
18.6 IPS
 
Object Detection (HP)
100% 12468
988.9 IPS
 
Object Detection (Q)
86% 18310
1.47 KIPS
 
Face Detection (SP)
100% 580
6.89 IPS
 
Face Detection (HP)
100% 24633
292.7 IPS
 
Face Detection (Q)
97% 83619
997.2 IPS
 
Depth Estimation (SP)
100% 511
3.93 IPS
 
Depth Estimation (HP)
99% 44946
346.3 IPS
 
Depth Estimation (Q)
63% 104316
982.5 IPS
 
Style Transfer (SP)
100% 838
1.08 IPS
 
Style Transfer (HP)
100% 56181
72.2 IPS
 
Style Transfer (Q)
98% 286739
369.8 IPS
 
Image Super-Resolution (SP)
100% 270
9.99 IPS
 
Image Super-Resolution (HP)
100% 32924
1.22 KIPS
 
Image Super-Resolution (Q)
97% 82534
3.06 KIPS
 
Text Classification (SP)
100% 332
443.7 IPS
 
Text Classification (HP)
100% 2827
3.77 KIPS
 
Text Classification (Q)
93% 8201
11.0 KIPS
 
Machine Translation (SP)
100% 579
9.97 IPS
 
Machine Translation (HP)
100% 4248
73.2 IPS
 
Machine Translation (Q)
55% 2315
60.7 IPS
 

Compare

Set Baseline Geekbench 6 now available