Geekbench ML Score

117
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date June 17 2025 09:30 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 CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 42
7.89 IPS
 
Image Classification (F16)
100% 42
7.88 IPS
 
Image Classification (I8)
97% 46
8.67 IPS
 
Image Segmentation (F32)
100% 172
2.87 IPS
 
Image Segmentation (F16)
100% 170
2.85 IPS
 
Image Segmentation (I8)
98% 190
3.18 IPS
 
Pose Estimation (F32)
100% 475
0.58 IPS
 
Pose Estimation (F16)
100% 487
0.59 IPS
 
Pose Estimation (I8)
100% 1431
1.73 IPS
 
Object Detection (F32)
100% 65
4.84 IPS
 
Object Detection (F16)
100% 64
4.77 IPS
 
Object Detection (I8)
61% 76
5.71 IPS
 
Face Detection (F32)
100% 214
2.55 IPS
 
Face Detection (F16)
100% 216
2.57 IPS
 
Face Detection (I8)
86% 260
3.09 IPS
 
Depth Estimation (F32)
100% 207
1.61 IPS
 
Depth Estimation (F16)
100% 211
1.64 IPS
 
Depth Estimation (I8)
95% 268
2.08 IPS
 
Style Transfer (F32)
100% 784
1.03 IPS
 
Style Transfer (F16)
100% 791
1.04 IPS
 
Style Transfer (I8)
98% 2110
2.78 IPS
 
Image Super-Resolution (F32)
100% 119
4.25 IPS
 
Image Super-Resolution (F16)
100% 121
4.33 IPS
 
Image Super-Resolution (I8)
98% 172
6.14 IPS
 
Text Classification (F32)
100% 8
11.2 IPS
 
Text Classification (F16)
100% 8
11.2 IPS
 
Text Classification (I8)
92% 9
12.6 IPS
 
Machine Translation (F32)
100% 21
0.39 IPS
 
Machine Translation (F16)
100% 21
0.39 IPS
 
Machine Translation (I8)
64% 22
0.40 IPS
 

Compare

Set Baseline Geekbench 6 now available