Geekbench ML Score

487
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date May 15 2025 09:38 AM
Views 1

System Information

System Information
Operating System Android 15
Model vivo V2361A
Model IDvivo V2361A
Motherboard crow
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3405 revision 1
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.40 GHz
Cluster 31 Core @ 2.63 GHz
Memory Information
Size 7.10 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 318
59.5 IPS
 
Image Classification (F16)
100% 389
72.8 IPS
 
Image Classification (I8)
99% 342
64.0 IPS
 
Image Segmentation (F32)
100% 554
9.25 IPS
 
Image Segmentation (F16)
100% 881
14.7 IPS
 
Image Segmentation (I8)
98% 733
12.2 IPS
 
Pose Estimation (F32)
100% 324
0.39 IPS
 
Pose Estimation (F16)
100% 686
0.83 IPS
 
Pose Estimation (I8)
100% 674
0.82 IPS
 
Object Detection (F32)
100% 220
16.4 IPS
 
Object Detection (F16)
100% 185
13.8 IPS
 
Object Detection (I8)
62% 187
14.0 IPS
 
Face Detection (F32)
100% 998
11.9 IPS
 
Face Detection (F16)
97% 1441
17.1 IPS
 
Face Detection (I8)
86% 1221
14.5 IPS
 
Depth Estimation (F32)
100% 672
5.21 IPS
 
Depth Estimation (F16)
100% 1307
10.1 IPS
 
Depth Estimation (I8)
95% 1287
9.98 IPS
 
Style Transfer (F32)
100% 1647
2.17 IPS
 
Style Transfer (F16)
100% 3648
4.80 IPS
 
Style Transfer (I8)
98% 3600
4.74 IPS
 
Image Super-Resolution (F32)
100% 214
7.64 IPS
 
Image Super-Resolution (F16)
100% 317
11.3 IPS
 
Image Super-Resolution (I8)
98% 306
10.9 IPS
 
Text Classification (F32)
100% 103
147.5 IPS
 
Text Classification (F16)
100% 47
67.4 IPS
 
Text Classification (I8)
92% 159
228.0 IPS
 
Machine Translation (F32)
100% 313
5.75 IPS
 
Machine Translation (F16)
100% 314
5.79 IPS
 
Machine Translation (I8)
64% 380
6.99 IPS
 

Compare

Set Baseline Geekbench 6 now available