Geekbench AI Score

262
Single Precision Score
243
Half Precision Score
553
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

User y561994
Upload Date November 28 2025 06:58 PM
Views 6

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% 135
25.1 IPS
 
Image Classification (Q)
99% 364
67.8 IPS
 
Image Segmentation (SP)
100% 178
2.89 IPS
 
Image Segmentation (HP)
100% 179
2.90 IPS
 
Image Segmentation (Q)
98% 372
6.06 IPS
 
Pose Estimation (SP)
100% 248
0.29 IPS
 
Pose Estimation (HP)
100% 271
0.32 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% 394
31.6 IPS
 
Face Detection (SP)
100% 375
4.46 IPS
 
Face Detection (HP)
100% 375
4.46 IPS
 
Face Detection (Q)
97% 813
9.70 IPS
 
Depth Estimation (SP)
100% 318
2.45 IPS
 
Depth Estimation (HP)
99% 329
2.53 IPS
 
Depth Estimation (Q)
64% 751
6.81 IPS
 
Style Transfer (SP)
100% 594
0.76 IPS
 
Style Transfer (HP)
100% 596
0.77 IPS
 
Style Transfer (Q)
98% 1655
2.13 IPS
 
Image Super-Resolution (SP)
100% 158
5.83 IPS
 
Image Super-Resolution (HP)
100% 158
5.82 IPS
 
Image Super-Resolution (Q)
97% 554
20.5 IPS
 
Text Classification (SP)
100% 202
269.1 IPS
 
Text Classification (HP)
100% 202
270.1 IPS
 
Text Classification (Q)
91% 335
450.1 IPS
 
Machine Translation (SP)
100% 354
6.10 IPS
 
Machine Translation (HP)
100% 358
6.17 IPS
 
Machine Translation (Q)
57% 288
7.04 IPS
 

Compare

Set Baseline Geekbench 6 now available