Geekbench AI Score

294
Single Precision Score
25172
Half Precision Score
55204
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date April 16 2025 09:16 PM
Views 9

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
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% 333
62.0 IPS
 
Image Classification (HP)
100% 18733
3.48 KIPS
 
Image Classification (Q)
97% 40745
7.60 KIPS
 
Image Segmentation (SP)
100% 500
8.11 IPS
 
Image Segmentation (HP)
100% 12856
208.4 IPS
 
Image Segmentation (Q)
98% 36830
598.9 IPS
 
Pose Estimation (SP)
100% 249
0.29 IPS
 
Pose Estimation (HP)
100% 121200
141.4 IPS
 
Pose Estimation (Q)
98% 471881
552.3 IPS
 
Object Detection (SP)
100% 137
10.9 IPS
 
Object Detection (HP)
100% 16959
1.35 KIPS
 
Object Detection (Q)
85% 19997
1.61 KIPS
 
Face Detection (SP)
100% 383
4.55 IPS
 
Face Detection (HP)
100% 35510
421.9 IPS
 
Face Detection (Q)
97% 110474
1.32 KIPS
 
Depth Estimation (SP)
100% 322
2.48 IPS
 
Depth Estimation (HP)
99% 78327
603.5 IPS
 
Depth Estimation (Q)
63% 133240
1.23 KIPS
 
Style Transfer (SP)
100% 600
0.77 IPS
 
Style Transfer (HP)
98% 98069
126.5 IPS
 
Style Transfer (Q)
98% 487998
629.3 IPS
 
Image Super-Resolution (SP)
100% 161
5.95 IPS
 
Image Super-Resolution (HP)
100% 51284
1.89 KIPS
 
Image Super-Resolution (Q)
97% 123964
4.59 KIPS
 
Text Classification (SP)
100% 200
266.7 IPS
 
Text Classification (HP)
100% 3892
5.20 KIPS
 
Text Classification (Q)
93% 7975
10.7 KIPS
 
Machine Translation (SP)
100% 359
6.19 IPS
 
Machine Translation (HP)
100% 3791
65.3 IPS
 
Machine Translation (Q)
56% 2614
67.3 IPS
 

Compare

Set Baseline Geekbench 6 now available