Geekbench ML Score

324
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date May 26 2025 10:49 PM
Views 5

System Information

System Information
Operating System Android 15
Model OnePlus CPH2723
Model IDOnePlus CPH2723
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
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 291
54.4 IPS
 
Image Classification (F16)
100% 308
57.7 IPS
 
Image Classification (I8)
97% 332
62.0 IPS
 
Image Segmentation (F32)
100% 159
2.65 IPS
 
Image Segmentation (F16)
100% 159
2.65 IPS
 
Image Segmentation (I8)
98% 381
6.36 IPS
 
Pose Estimation (F32)
100% 427
0.52 IPS
 
Pose Estimation (F16)
100% 223
0.27 IPS
 
Pose Estimation (I8)
100% 823
1.00 IPS
 
Object Detection (F32)
100% 132
9.86 IPS
 
Object Detection (F16)
100% 134
10.0 IPS
 
Object Detection (I8)
61% 355
26.5 IPS
 
Face Detection (F32)
100% 352
4.18 IPS
 
Face Detection (F16)
100% 352
4.18 IPS
 
Face Detection (I8)
86% 761
9.05 IPS
 
Depth Estimation (F32)
100% 318
2.47 IPS
 
Depth Estimation (F16)
100% 297
2.30 IPS
 
Depth Estimation (I8)
95% 814
6.31 IPS
 
Style Transfer (F32)
100% 556
0.73 IPS
 
Style Transfer (F16)
100% 542
0.71 IPS
 
Style Transfer (I8)
98% 1500
1.97 IPS
 
Image Super-Resolution (F32)
100% 149
5.32 IPS
 
Image Super-Resolution (F16)
100% 156
5.58 IPS
 
Image Super-Resolution (I8)
98% 529
18.9 IPS
 
Text Classification (F32)
100% 177
253.7 IPS
 
Text Classification (F16)
100% 178
255.5 IPS
 
Text Classification (I8)
92% 291
417.5 IPS
 
Machine Translation (F32)
100% 334
6.14 IPS
 
Machine Translation (F16)
100% 337
6.20 IPS
 
Machine Translation (I8)
64% 377
6.94 IPS
 

Compare

Set Baseline Geekbench 6 now available