Geekbench ML Score

109
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date December 17 2025 09:19 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 CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 58
10.9 IPS
 
Image Classification (F16)
100% 58
10.9 IPS
 
Image Classification (I8)
97% 85
15.8 IPS
 
Image Segmentation (F32)
100% 76
1.27 IPS
 
Image Segmentation (F16)
100% 76
1.27 IPS
 
Image Segmentation (I8)
98% 88
1.47 IPS
 
Pose Estimation (F32)
100% 117
0.14 IPS
 
Pose Estimation (F16)
100% 115
0.14 IPS
 
Pose Estimation (I8)
100% 213
0.26 IPS
 
Object Detection (F32)
100% 60
4.48 IPS
 
Object Detection (F16)
100% 60
4.50 IPS
 
Object Detection (I8)
61% 92
6.84 IPS
 
Face Detection (F32)
100% 135
1.60 IPS
 
Face Detection (F16)
100% 135
1.60 IPS
 
Face Detection (I8)
86% 219
2.61 IPS
 
Depth Estimation (F32)
100% 127
0.98 IPS
 
Depth Estimation (F16)
100% 126
0.98 IPS
 
Depth Estimation (I8)
95% 202
1.57 IPS
 
Style Transfer (F32)
100% 214
0.28 IPS
 
Style Transfer (F16)
100% 213
0.28 IPS
 
Style Transfer (I8)
98% 402
0.53 IPS
 
Image Super-Resolution (F32)
100% 71
2.54 IPS
 
Image Super-Resolution (F16)
100% 71
2.53 IPS
 
Image Super-Resolution (I8)
98% 132
4.72 IPS
 
Text Classification (F32)
100% 74
105.8 IPS
 
Text Classification (F16)
100% 73
105.1 IPS
 
Text Classification (I8)
92% 71
102.5 IPS
 
Machine Translation (F32)
100% 141
2.60 IPS
 
Machine Translation (F16)
100% 139
2.56 IPS
 
Machine Translation (I8)
64% 83
1.52 IPS
 

Compare

Set Baseline Geekbench 6 now available