Geekbench AI Score

183
Single Precision Score
180
Half Precision Score
9026
Quantized Score
Geekbench AI 1.4.0 for Android AArch64

Result Information

User xRoach
Upload Date August 27 2025 07:28 PM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device ARM ARMv8
System Information
Operating System Android 15
Model samsung SM-G736U1
Model IDsamsung SM-G736U1
Motherboard lahaina
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.40 GHz
Memory Information
Size 5.25 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 125
23.2 IPS
 
Image Classification (HP)
100% 125
23.3 IPS
 
Image Classification (Q)
99% 7335
1.37 KIPS
 
Image Segmentation (SP)
100% 168
2.72 IPS
 
Image Segmentation (HP)
100% 168
2.73 IPS
 
Image Segmentation (Q)
98% 5603
91.1 IPS
 
Pose Estimation (SP)
100% 225
0.26 IPS
 
Pose Estimation (HP)
100% 226
0.26 IPS
 
Pose Estimation (Q)
94% 42177
49.5 IPS
 
Object Detection (SP)
100% 124
9.81 IPS
 
Object Detection (HP)
100% 124
9.85 IPS
 
Object Detection (Q)
88% 3757
301.0 IPS
 
Face Detection (SP)
100% 312
3.70 IPS
 
Face Detection (HP)
100% 315
3.74 IPS
 
Face Detection (Q)
97% 17685
210.9 IPS
 
Depth Estimation (SP)
100% 275
2.12 IPS
 
Depth Estimation (HP)
99% 275
2.12 IPS
 
Depth Estimation (Q)
64% 18331
168.8 IPS
 
Style Transfer (SP)
100% 384
0.49 IPS
 
Style Transfer (HP)
100% 334
0.43 IPS
 
Style Transfer (Q)
98% 80502
103.8 IPS
 
Image Super-Resolution (SP)
100% 91
3.35 IPS
 
Image Super-Resolution (HP)
100% 91
3.34 IPS
 
Image Super-Resolution (Q)
97% 21864
810.2 IPS
 
Text Classification (SP)
100% 118
157.3 IPS
 
Text Classification (HP)
100% 118
157.2 IPS
 
Text Classification (Q)
94% 2416
3.24 KIPS
 
Machine Translation (SP)
100% 204
3.51 IPS
 
Machine Translation (HP)
100% 203
3.50 IPS
 
Machine Translation (Q)
50% 400
13.8 IPS
 

Compare

Set Baseline Geekbench 6 now available