Geekbench AI Score

569
Single Precision Score
556
Half Precision Score
1186
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

User AllieWolfie
Upload Date August 14 2025 08:51 AM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device Qualcomm Snapdragon 8 Elite
System Information
Operating System Android 15
Model Samsung Galaxy S25
Model IDsamsung SM-S931B
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 10.86 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 414
77.1 IPS
 
Image Classification (HP)
100% 417
77.6 IPS
 
Image Classification (Q)
99% 1041
194.2 IPS
 
Image Segmentation (SP)
100% 504
8.16 IPS
 
Image Segmentation (HP)
100% 516
8.36 IPS
 
Image Segmentation (Q)
98% 1081
17.6 IPS
 
Pose Estimation (SP)
100% 622
0.73 IPS
 
Pose Estimation (HP)
100% 565
0.66 IPS
 
Pose Estimation (Q)
98% 2150
2.52 IPS
 
Object Detection (SP)
100% 334
26.5 IPS
 
Object Detection (HP)
100% 334
26.5 IPS
 
Object Detection (Q)
87% 780
62.6 IPS
 
Face Detection (SP)
100% 785
9.33 IPS
 
Face Detection (HP)
100% 790
9.38 IPS
 
Face Detection (Q)
97% 1781
21.2 IPS
 
Depth Estimation (SP)
100% 695
5.36 IPS
 
Depth Estimation (HP)
99% 613
4.72 IPS
 
Depth Estimation (Q)
64% 1359
12.3 IPS
 
Style Transfer (SP)
100% 1229
1.58 IPS
 
Style Transfer (HP)
100% 1097
1.41 IPS
 
Style Transfer (Q)
98% 2971
3.83 IPS
 
Image Super-Resolution (SP)
100% 339
12.5 IPS
 
Image Super-Resolution (HP)
100% 339
12.5 IPS
 
Image Super-Resolution (Q)
97% 1202
44.6 IPS
 
Text Classification (SP)
100% 435
580.2 IPS
 
Text Classification (HP)
100% 435
580.1 IPS
 
Text Classification (Q)
91% 775
1.04 KIPS
 
Machine Translation (SP)
100% 838
14.4 IPS
 
Machine Translation (HP)
100% 891
15.3 IPS
 
Machine Translation (Q)
57% 438
10.7 IPS
 

Compare

Set Baseline Geekbench 6 now available