Geekbench AI Score

440
Single Precision Score
31602
Half Precision Score
78105
Quantized Score
Geekbench AI 1.6.1 for Android AArch64

Result Information

Upload Date January 25 2026 06:37 PM
Views 18

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm ARMv8
System Information
Operating System Android 16
Model vivo V2505A
Model IDvivo V2505A
Motherboard canoe
Governorwalt
CPU Information
Name Qualcomm ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 3 part 2
Base Frequency 3.63 GHz
Cluster 16 Cores @ 3.63 GHz
Cluster 22 Cores @ 4.61 GHz
Memory Information
Size 14.87 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 283
52.6 IPS
 
Image Classification (HP)
100% 24915
4.63 KIPS
 
Image Classification (Q)
96% 50692
9.47 KIPS
 
Image Segmentation (SP)
100% 374
6.06 IPS
 
Image Segmentation (HP)
100% 16343
264.9 IPS
 
Image Segmentation (Q)
98% 61781
1.00 KIPS
 
Pose Estimation (SP)
100% 503
0.59 IPS
 
Pose Estimation (HP)
100% 162439
189.5 IPS
 
Pose Estimation (Q)
98% 624710
731.2 IPS
 
Object Detection (SP)
100% 244
19.4 IPS
 
Object Detection (HP)
100% 23741
1.88 KIPS
 
Object Detection (Q)
85% 31515
2.54 KIPS
 
Face Detection (SP)
100% 685
8.14 IPS
 
Face Detection (HP)
100% 47158
560.3 IPS
 
Face Detection (Q)
97% 149212
1.78 KIPS
 
Depth Estimation (SP)
100% 572
4.41 IPS
 
Depth Estimation (HP)
99% 92227
710.6 IPS
 
Depth Estimation (Q)
63% 201291
1.87 KIPS
 
Style Transfer (SP)
100% 1034
1.33 IPS
 
Style Transfer (HP)
100% 97945
125.9 IPS
 
Style Transfer (Q)
98% 591692
763.0 IPS
 
Image Super-Resolution (SP)
100% 267
9.85 IPS
 
Image Super-Resolution (HP)
100% 55491
2.05 KIPS
 
Image Super-Resolution (Q)
97% 170067
6.30 KIPS
 
Text Classification (SP)
100% 328
437.2 IPS
 
Text Classification (HP)
100% 4293
5.73 KIPS
 
Text Classification (Q)
93% 10535
14.1 KIPS
 
Machine Translation (SP)
100% 597
10.3 IPS
 
Machine Translation (HP)
100% 6236
107.4 IPS
 
Machine Translation (Q)
56% 4304
110.9 IPS
 

Compare

Set Baseline Geekbench 6 now available