Geekbench AI Score

469
Single Precision Score
474
Half Precision Score
988
Quantized Score
Geekbench AI 1.6.1 for Android AArch64

Result Information

User ixhayabusa
Upload Date January 18 2026 08:41 PM
Views 5

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device Qualcomm Snapdragon 8 Elite
System Information
Operating System Android 16
Model Samsung Galaxy S25 Ultra
Model IDsamsung SM-S938B
Motherboard sun
Governorwalt
CPU Information
Name Qualcomm ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 3 part 1 revision 4
Base Frequency 3.53 GHz
Cluster 16 Cores @ 3.53 GHz
Cluster 22 Cores @ 4.47 GHz
Memory Information
Size 10.85 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 399
74.2 IPS
 
Image Classification (HP)
100% 405
75.3 IPS
 
Image Classification (Q)
99% 1031
192.3 IPS
 
Image Segmentation (SP)
100% 374
6.06 IPS
 
Image Segmentation (HP)
100% 375
6.08 IPS
 
Image Segmentation (Q)
98% 702
11.4 IPS
 
Pose Estimation (SP)
100% 521
0.61 IPS
 
Pose Estimation (HP)
100% 466
0.54 IPS
 
Pose Estimation (Q)
98% 1944
2.28 IPS
 
Object Detection (SP)
100% 277
22.0 IPS
 
Object Detection (HP)
100% 261
20.7 IPS
 
Object Detection (Q)
87% 676
54.2 IPS
 
Face Detection (SP)
100% 695
8.25 IPS
 
Face Detection (HP)
100% 695
8.26 IPS
 
Face Detection (Q)
97% 1427
17.0 IPS
 
Depth Estimation (SP)
100% 558
4.30 IPS
 
Depth Estimation (HP)
99% 561
4.32 IPS
 
Depth Estimation (Q)
64% 1210
11.0 IPS
 
Style Transfer (SP)
100% 954
1.23 IPS
 
Style Transfer (HP)
100% 1044
1.34 IPS
 
Style Transfer (Q)
98% 2333
3.01 IPS
 
Image Super-Resolution (SP)
100% 247
9.11 IPS
 
Image Super-Resolution (HP)
100% 288
10.6 IPS
 
Image Super-Resolution (Q)
97% 1019
37.8 IPS
 
Text Classification (SP)
100% 369
491.9 IPS
 
Text Classification (HP)
100% 369
492.1 IPS
 
Text Classification (Q)
91% 567
762.1 IPS
 
Machine Translation (SP)
100% 722
12.4 IPS
 
Machine Translation (HP)
100% 724
12.5 IPS
 
Machine Translation (Q)
57% 404
9.88 IPS
 

Compare

Set Baseline Geekbench 6 now available