Geekbench ML Score

55
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date December 19 2025 09:03 AM
Views 3

System Information

System Information
Operating System Android 12
Model telechips TCC803X_LCN
Model IDtelechips TCC803X_LCN
Motherboard tcc803x_android_avn
CPU Information
Name ARM ARMv8
Topology 1 Processor, 4 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3331 revision 4
Base Frequency 0 MHz
Cluster 14 Cores
Memory Information
Size 2.80 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 33
6.27 IPS
 
Image Classification (F16)
100% 51
9.46 IPS
 
Image Classification (I8)
97% 49
9.15 IPS
 
Image Segmentation (F32)
100% 44
0.73 IPS
 
Image Segmentation (F16)
100% 64
1.07 IPS
 
Image Segmentation (I8)
98% 62
1.04 IPS
 
Pose Estimation (F32)
100% 30
0.04 IPS
 
Pose Estimation (F16)
100% 38
0.05 IPS
 
Pose Estimation (I8)
100% 38
0.05 IPS
 
Object Detection (F32)
100% 30
2.23 IPS
 
Object Detection (F16)
100% 44
3.28 IPS
 
Object Detection (I8)
62% 44
3.25 IPS
 
Face Detection (F32)
100% 118
1.41 IPS
 
Face Detection (F16)
98% 160
1.91 IPS
 
Face Detection (I8)
86% 150
1.79 IPS
 
Depth Estimation (F32)
100% 64
0.50 IPS
 
Depth Estimation (F16)
100% 88
0.69 IPS
 
Depth Estimation (I8)
95% 82
0.63 IPS
 
Style Transfer (F32)
100% 119
0.16 IPS
 
Style Transfer (F16)
100% 169
0.22 IPS
 
Style Transfer (I8)
98% 169
0.22 IPS
 
Image Super-Resolution (F32)
100% 36
1.29 IPS
 
Image Super-Resolution (F16)
100% 51
1.83 IPS
 
Image Super-Resolution (I8)
98% 51
1.81 IPS
 
Text Classification (F32)
100% 24
34.3 IPS
 
Text Classification (F16)
100% 24
34.4 IPS
 
Text Classification (I8)
92% 32
45.4 IPS
 
Machine Translation (F32)
100% 47
0.87 IPS
 
Machine Translation (F16)
100% 47
0.86 IPS
 
Machine Translation (I8)
64% 45
0.83 IPS
 

Compare

Set Baseline Geekbench 6 now available