Geekbench ML Score

249
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date June 17 2025 09:46 AM
Views 5

System Information

System Information
Operating System Android 12
Model DTEN Bar_DCR200
Model IDDTEN Bar_DCR200
Motherboard R1-003
Governorperformance
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.35 GHz
Memory Information
Size 15.33 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 115
21.6 IPS
 
Image Classification (F16)
100% 115
21.6 IPS
 
Image Classification (I8)
97% 261
48.8 IPS
 
Image Segmentation (F32)
100% 149
2.49 IPS
 
Image Segmentation (F16)
100% 150
2.50 IPS
 
Image Segmentation (I8)
98% 279
4.66 IPS
 
Pose Estimation (F32)
100% 193
0.23 IPS
 
Pose Estimation (F16)
100% 195
0.24 IPS
 
Pose Estimation (I8)
100% 758
0.92 IPS
 
Object Detection (F32)
100% 120
8.95 IPS
 
Object Detection (F16)
100% 120
8.96 IPS
 
Object Detection (I8)
61% 294
21.9 IPS
 
Face Detection (F32)
100% 285
3.39 IPS
 
Face Detection (F16)
100% 285
3.39 IPS
 
Face Detection (I8)
86% 593
7.05 IPS
 
Depth Estimation (F32)
100% 239
1.86 IPS
 
Depth Estimation (F16)
100% 240
1.86 IPS
 
Depth Estimation (I8)
95% 647
5.02 IPS
 
Style Transfer (F32)
100% 395
0.52 IPS
 
Style Transfer (F16)
100% 395
0.52 IPS
 
Style Transfer (I8)
98% 1190
1.57 IPS
 
Image Super-Resolution (F32)
100% 125
4.45 IPS
 
Image Super-Resolution (F16)
100% 125
4.45 IPS
 
Image Super-Resolution (I8)
98% 460
16.4 IPS
 
Text Classification (F32)
100% 156
223.6 IPS
 
Text Classification (F16)
100% 156
223.6 IPS
 
Text Classification (I8)
92% 256
367.8 IPS
 
Machine Translation (F32)
100% 277
5.10 IPS
 
Machine Translation (F16)
100% 280
5.16 IPS
 
Machine Translation (I8)
64% 266
4.90 IPS
 

Compare

Set Baseline Geekbench 6 now available