Geekbench AI Score

1202
Single Precision Score
1258
Half Precision Score
1858
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date June 17 2025 11:26 AM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
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 14.83 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1780
331.1 IPS
 
Image Classification (HP)
100% 1601
297.7 IPS
 
Image Classification (Q)
100% 1509
280.5 IPS
 
Image Segmentation (SP)
100% 993
16.1 IPS
 
Image Segmentation (HP)
100% 947
15.3 IPS
 
Image Segmentation (Q)
98% 2170
35.3 IPS
 
Pose Estimation (SP)
100% 2272
2.65 IPS
 
Pose Estimation (HP)
100% 2207
2.58 IPS
 
Pose Estimation (Q)
84% 5086
6.03 IPS
 
Object Detection (SP)
98% 688
54.7 IPS
 
Object Detection (HP)
98% 690
54.9 IPS
 
Object Detection (Q)
83% 1306
105.5 IPS
 
Face Detection (SP)
100% 1698
20.2 IPS
 
Face Detection (HP)
100% 1911
22.7 IPS
 
Face Detection (Q)
95% 3541
42.3 IPS
 
Depth Estimation (SP)
99% 1796
13.9 IPS
 
Depth Estimation (HP)
99% 1816
14.0 IPS
 
Depth Estimation (Q)
64% 3400
31.1 IPS
 
Style Transfer (SP)
89% 4720
6.13 IPS
 
Style Transfer (HP)
89% 4473
5.81 IPS
 
Style Transfer (Q)
98% 9551
12.3 IPS
 
Image Super-Resolution (SP)
100% 992
36.6 IPS
 
Image Super-Resolution (HP)
100% 1059
39.1 IPS
 
Image Super-Resolution (Q)
97% 2300
85.2 IPS
 
Text Classification (SP)
100% 259
346.2 IPS
 
Text Classification (HP)
99% 400
533.9 IPS
 
Text Classification (Q)
88% 327
440.4 IPS
 
Machine Translation (SP)
100% 620
10.7 IPS
 
Machine Translation (HP)
100% 659
11.4 IPS
 
Machine Translation (Q)
50% 261
9.25 IPS
 

Compare

Set Baseline Geekbench 6 now available