Geekbench ML Score

375
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date December 17 2025 07:19 AM
Views 1

System Information

System Information
Operating System Android 14
Model telechips TCC8070_AVN
Model IDtelechips TCC8070_AVN
Motherboard tcc807x_android_avn
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 1
Base Frequency 0 MHz
Cluster 18 Cores
Memory Information
Size 5.54 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 275
51.4 IPS
 
Image Classification (F16)
100% 517
96.7 IPS
 
Image Classification (I8)
97% 497
92.9 IPS
 
Image Segmentation (F32)
100% 399
6.67 IPS
 
Image Segmentation (F16)
100% 613
10.2 IPS
 
Image Segmentation (I8)
98% 596
9.95 IPS
 
Pose Estimation (F32)
100% 202
0.24 IPS
 
Pose Estimation (F16)
100% 245
0.30 IPS
 
Pose Estimation (I8)
100% 245
0.30 IPS
 
Object Detection (F32)
100% 226
16.9 IPS
 
Object Detection (F16)
100% 365
27.2 IPS
 
Object Detection (I8)
62% 366
27.4 IPS
 
Face Detection (F32)
100% 933
11.1 IPS
 
Face Detection (F16)
98% 1444
17.2 IPS
 
Face Detection (I8)
86% 1363
16.2 IPS
 
Depth Estimation (F32)
100% 415
3.22 IPS
 
Depth Estimation (F16)
100% 561
4.35 IPS
 
Depth Estimation (I8)
95% 557
4.32 IPS
 
Style Transfer (F32)
100% 834
1.10 IPS
 
Style Transfer (F16)
100% 1229
1.62 IPS
 
Style Transfer (I8)
98% 1228
1.62 IPS
 
Image Super-Resolution (F32)
100% 260
9.29 IPS
 
Image Super-Resolution (F16)
100% 403
14.4 IPS
 
Image Super-Resolution (I8)
98% 400
14.3 IPS
 
Text Classification (F32)
100% 74
106.4 IPS
 
Text Classification (F16)
100% 74
106.4 IPS
 
Text Classification (I8)
92% 163
233.5 IPS
 
Machine Translation (F32)
100% 143
2.64 IPS
 
Machine Translation (F16)
100% 145
2.68 IPS
 
Machine Translation (I8)
64% 192
3.54 IPS
 

Compare

Set Baseline Geekbench 6 now available