Geekbench AI Score

263
Single Precision Score
241
Half Precision Score
554
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

User y561994
Upload Date December 06 2025 12:10 AM
Views 3

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% 329
61.2 IPS
 
Image Classification (HP)
100% 135
25.0 IPS
 
Image Classification (Q)
99% 361
67.3 IPS
 
Image Segmentation (SP)
100% 177
2.88 IPS
 
Image Segmentation (HP)
100% 179
2.90 IPS
 
Image Segmentation (Q)
98% 374
6.08 IPS
 
Pose Estimation (SP)
100% 249
0.29 IPS
 
Pose Estimation (HP)
100% 247
0.29 IPS
 
Pose Estimation (Q)
98% 938
1.10 IPS
 
Object Detection (SP)
100% 135
10.7 IPS
 
Object Detection (HP)
100% 135
10.7 IPS
 
Object Detection (Q)
87% 395
31.7 IPS
 
Face Detection (SP)
100% 377
4.48 IPS
 
Face Detection (HP)
100% 376
4.47 IPS
 
Face Detection (Q)
97% 818
9.75 IPS
 
Depth Estimation (SP)
100% 318
2.45 IPS
 
Depth Estimation (HP)
99% 318
2.45 IPS
 
Depth Estimation (Q)
64% 756
6.86 IPS
 
Style Transfer (SP)
100% 597
0.77 IPS
 
Style Transfer (HP)
100% 598
0.77 IPS
 
Style Transfer (Q)
98% 1659
2.14 IPS
 
Image Super-Resolution (SP)
100% 159
5.87 IPS
 
Image Super-Resolution (HP)
100% 159
5.86 IPS
 
Image Super-Resolution (Q)
97% 553
20.5 IPS
 
Text Classification (SP)
100% 203
270.9 IPS
 
Text Classification (HP)
100% 202
269.3 IPS
 
Text Classification (Q)
91% 335
450.4 IPS
 
Machine Translation (SP)
100% 355
6.12 IPS
 
Machine Translation (HP)
100% 360
6.20 IPS
 
Machine Translation (Q)
57% 288
7.04 IPS
 

Compare

Set Baseline Geekbench 6 now available