Geekbench ML Score

486
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date June 17 2025 07:43 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 GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 325
60.8 IPS
 
Image Classification (F16)
100% 485
90.7 IPS
 
Image Classification (I8)
97% 467
87.4 IPS
 
Image Segmentation (F32)
100% 461
7.70 IPS
 
Image Segmentation (F16)
100% 626
10.5 IPS
 
Image Segmentation (I8)
98% 611
10.2 IPS
 
Pose Estimation (F32)
100% 318
0.39 IPS
 
Pose Estimation (F16)
100% 432
0.52 IPS
 
Pose Estimation (I8)
100% 432
0.52 IPS
 
Object Detection (F32)
100% 261
19.5 IPS
 
Object Detection (F16)
100% 381
28.5 IPS
 
Object Detection (I8)
62% 381
28.5 IPS
 
Face Detection (F32)
100% 997
11.9 IPS
 
Face Detection (F16)
98% 1254
14.9 IPS
 
Face Detection (I8)
86% 1189
14.1 IPS
 
Depth Estimation (F32)
100% 609
4.72 IPS
 
Depth Estimation (F16)
100% 731
5.67 IPS
 
Depth Estimation (I8)
95% 727
5.64 IPS
 
Style Transfer (F32)
100% 1437
1.89 IPS
 
Style Transfer (F16)
100% 1772
2.33 IPS
 
Style Transfer (I8)
98% 1771
2.33 IPS
 
Image Super-Resolution (F32)
100% 320
11.4 IPS
 
Image Super-Resolution (F16)
100% 398
14.2 IPS
 
Image Super-Resolution (I8)
98% 395
14.1 IPS
 
Text Classification (F32)
100% 156
223.5 IPS
 
Text Classification (F16)
100% 155
223.2 IPS
 
Text Classification (I8)
92% 255
367.1 IPS
 
Machine Translation (F32)
100% 277
5.10 IPS
 
Machine Translation (F16)
100% 281
5.16 IPS
 
Machine Translation (I8)
64% 267
4.91 IPS
 

Compare

Set Baseline Geekbench 6 now available