Geekbench ML Score

831
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date June 14 2025 11:55 AM
Views 3

System Information

System Information
Operating System Android 14
Model OnePlus PJD110
Model IDOnePlus PJD110
Motherboard pineapple
Governoruag
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3458 revision 1
Base Frequency 2.26 GHz
Cluster 12 Cores @ 2.27 GHz
Cluster 25 Cores @ 2.96 GHz
Cluster 31 Core @ 3.19 GHz
Memory Information
Size 14.90 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 462
86.4 IPS
 
Image Classification (F16)
100% 581
108.7 IPS
 
Image Classification (I8)
99% 549
102.7 IPS
 
Image Segmentation (F32)
100% 652
10.9 IPS
 
Image Segmentation (F16)
100% 1049
17.5 IPS
 
Image Segmentation (I8)
98% 1027
17.2 IPS
 
Pose Estimation (F32)
100% 658
0.80 IPS
 
Pose Estimation (F16)
100% 1368
1.66 IPS
 
Pose Estimation (I8)
100% 1422
1.72 IPS
 
Object Detection (F32)
100% 253
18.9 IPS
 
Object Detection (F16)
100% 279
20.8 IPS
 
Object Detection (I8)
62% 264
19.7 IPS
 
Face Detection (F32)
100% 1554
18.5 IPS
 
Face Detection (F16)
97% 2751
32.7 IPS
 
Face Detection (I8)
86% 2302
27.4 IPS
 
Depth Estimation (F32)
100% 1006
7.81 IPS
 
Depth Estimation (F16)
100% 2070
16.1 IPS
 
Depth Estimation (I8)
95% 2032
15.8 IPS
 
Style Transfer (F32)
100% 3612
4.75 IPS
 
Style Transfer (F16)
100% 5878
7.73 IPS
 
Style Transfer (I8)
98% 5121
6.74 IPS
 
Image Super-Resolution (F32)
100% 307
11.0 IPS
 
Image Super-Resolution (F16)
100% 615
22.0 IPS
 
Image Super-Resolution (I8)
98% 614
21.9 IPS
 
Text Classification (F32)
100% 337
484.2 IPS
 
Text Classification (F16)
100% 334
480.5 IPS
 
Text Classification (I8)
92% 549
788.5 IPS
 
Machine Translation (F32)
100% 539
9.92 IPS
 
Machine Translation (F16)
100% 286
5.26 IPS
 
Machine Translation (I8)
64% 319
5.87 IPS
 

Compare

Set Baseline Geekbench 6 now available