Geekbench AI Score

1235
Single Precision Score
1730
Half Precision Score
1397
Quantized Score
Geekbench AI 1.6.1 for Android AArch64

Result Information

User Shakov9202
Upload Date January 24 2026 03:31 PM
Views 7

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM ARMv8
System Information
Operating System Android 16
Model vivo V2502A
Model IDvivo V2502A
Motherboard k6993v1_64
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3468
Base Frequency 2.70 GHz
Cluster 14 Cores @ 2.70 GHz
Cluster 23 Cores @ 3.50 GHz
Cluster 31 Core @ 4.21 GHz
Memory Information
Size 11.09 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 484
89.9 IPS
 
Image Classification (HP)
100% 790
146.9 IPS
 
Image Classification (Q)
97% 705
131.5 IPS
 
Image Segmentation (SP)
100% 1624
26.3 IPS
 
Image Segmentation (HP)
100% 2654
43.0 IPS
 
Image Segmentation (Q)
98% 2590
42.1 IPS
 
Pose Estimation (SP)
100% 8173
9.54 IPS
 
Pose Estimation (HP)
100% 14495
16.9 IPS
 
Pose Estimation (Q)
95% 13947
16.3 IPS
 
Object Detection (SP)
100% 494
39.2 IPS
 
Object Detection (HP)
99% 783
62.1 IPS
 
Object Detection (Q)
83% 762
61.6 IPS
 
Face Detection (SP)
100% 2785
33.1 IPS
 
Face Detection (HP)
100% 3962
47.1 IPS
 
Face Detection (Q)
96% 3037
36.2 IPS
 
Depth Estimation (SP)
100% 3610
27.8 IPS
 
Depth Estimation (HP)
98% 5360
41.4 IPS
 
Depth Estimation (Q)
62% 4168
39.6 IPS
 
Style Transfer (SP)
100% 12932
16.6 IPS
 
Style Transfer (HP)
100% 22966
29.5 IPS
 
Style Transfer (Q)
98% 22726
29.3 IPS
 
Image Super-Resolution (SP)
100% 1741
64.3 IPS
 
Image Super-Resolution (HP)
100% 2583
95.4 IPS
 
Image Super-Resolution (Q)
97% 2275
84.3 IPS
 
Text Classification (SP)
35% 27
244.0 IPS
 
Text Classification (HP)
29% 15
259.8 IPS
 
Text Classification (Q)
32% 19
240.5 IPS
 
Machine Translation (SP)
100% 428
7.37 IPS
 
Machine Translation (HP)
100% 537
9.26 IPS
 
Machine Translation (Q)
43% 118
6.84 IPS
 

Compare

Set Baseline Geekbench 6 now available