Geekbench AI Score

244
Single Precision Score
222
Half Precision Score
500
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

User y561994
Upload Date November 28 2025 06:13 PM
Views 4

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device Qualcomm SM8750
System Information
Operating System Android 15
Model HONOR PTP-N49
Model IDHONOR PTP-N49
Motherboard PTP
Governorwalt
CPU Information
Name Qualcomm SM8750
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 @ 4.32 GHz
Memory Information
Size 10.94 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 330
61.3 IPS
 
Image Classification (HP)
100% 126
23.5 IPS
 
Image Classification (Q)
99% 327
61.0 IPS
 
Image Segmentation (SP)
100% 163
2.65 IPS
 
Image Segmentation (HP)
100% 164
2.65 IPS
 
Image Segmentation (Q)
98% 344
5.59 IPS
 
Pose Estimation (SP)
100% 227
0.26 IPS
 
Pose Estimation (HP)
100% 225
0.26 IPS
 
Pose Estimation (Q)
98% 838
0.98 IPS
 
Object Detection (SP)
100% 122
9.71 IPS
 
Object Detection (HP)
100% 123
9.72 IPS
 
Object Detection (Q)
87% 347
27.8 IPS
 
Face Detection (SP)
100% 351
4.17 IPS
 
Face Detection (HP)
100% 353
4.19 IPS
 
Face Detection (Q)
97% 745
8.89 IPS
 
Depth Estimation (SP)
100% 299
2.31 IPS
 
Depth Estimation (HP)
99% 298
2.29 IPS
 
Depth Estimation (Q)
64% 680
6.17 IPS
 
Style Transfer (SP)
100% 552
0.71 IPS
 
Style Transfer (HP)
100% 554
0.71 IPS
 
Style Transfer (Q)
98% 1496
1.93 IPS
 
Image Super-Resolution (SP)
100% 144
5.31 IPS
 
Image Super-Resolution (HP)
100% 143
5.29 IPS
 
Image Super-Resolution (Q)
97% 511
18.9 IPS
 
Text Classification (SP)
100% 188
251.0 IPS
 
Text Classification (HP)
100% 188
251.0 IPS
 
Text Classification (Q)
91% 311
417.8 IPS
 
Machine Translation (SP)
100% 332
5.72 IPS
 
Machine Translation (HP)
100% 336
5.78 IPS
 
Machine Translation (Q)
57% 250
6.11 IPS
 

Compare

Set Baseline Geekbench 6 now available