Geekbench AI Score

475
Single Precision Score
26771
Half Precision Score
60140
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date February 02 2025 05:51 AM
Views 16

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm ARMv8
System Information
Operating System Android 15
Model vivo V2408A
Model IDvivo V2408A
Motherboard sun
Governorwalt
CPU Information
Name Qualcomm ARMv8
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 10.87 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 285
53.0 IPS
 
Image Classification (HP)
100% 20316
3.78 KIPS
 
Image Classification (Q)
97% 49068
9.16 KIPS
 
Image Segmentation (SP)
100% 377
6.11 IPS
 
Image Segmentation (HP)
100% 13623
220.8 IPS
 
Image Segmentation (Q)
98% 41011
666.9 IPS
 
Pose Estimation (SP)
100% 513
0.60 IPS
 
Pose Estimation (HP)
100% 123207
143.8 IPS
 
Pose Estimation (Q)
98% 475709
556.8 IPS
 
Object Detection (SP)
100% 267
21.2 IPS
 
Object Detection (HP)
100% 18657
1.48 KIPS
 
Object Detection (Q)
85% 21712
1.75 KIPS
 
Face Detection (SP)
100% 701
8.33 IPS
 
Face Detection (HP)
100% 40558
481.9 IPS
 
Face Detection (Q)
97% 136701
1.63 KIPS
 
Depth Estimation (SP)
100% 616
4.74 IPS
 
Depth Estimation (HP)
99% 83031
639.7 IPS
 
Depth Estimation (Q)
63% 141236
1.31 KIPS
 
Style Transfer (SP)
100% 1102
1.42 IPS
 
Style Transfer (HP)
98% 98590
127.1 IPS
 
Style Transfer (Q)
98% 490141
632.0 IPS
 
Image Super-Resolution (SP)
100% 315
11.6 IPS
 
Image Super-Resolution (HP)
100% 52685
1.95 KIPS
 
Image Super-Resolution (Q)
97% 132880
4.92 KIPS
 
Text Classification (SP)
100% 395
527.0 IPS
 
Text Classification (HP)
100% 3891
5.19 KIPS
 
Text Classification (Q)
93% 7953
10.7 KIPS
 
Machine Translation (SP)
100% 685
11.8 IPS
 
Machine Translation (HP)
100% 4368
75.2 IPS
 
Machine Translation (Q)
56% 2978
76.7 IPS
 

Compare

Set Baseline Geekbench 6 now available