Geekbench ML Score

164
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 20 2025 09:40 PM
Views 7

System Information

System Information
Operating System Android 11
Model LENOVO Lenovo TB-J606F
Model IDLENOVO Lenovo TB-J606F
Motherboard bengal
Governorschedutil
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 10 part 2048 revision 2
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.02 GHz
Memory Information
Size 3.58 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 125
13.4 IPS
 
Image Classification (F16)
100% 157
16.8 IPS
 
Image Classification (I8)
80% 798
85.5 IPS
 
Image Segmentation (F32)
100% 207
1.28 IPS
 
Image Segmentation (F16)
100% 252
1.56 IPS
 
Image Segmentation (I8)
89% 1608
9.93 IPS
 
Pose Estimation (F32)
100% 45
0.18 IPS
 
Pose Estimation (F16)
100% 83
0.34 IPS
 
Pose Estimation (I8)
80% 879
3.56 IPS
 
Object Detection (F32)
100% 143
5.01 IPS
 
Object Detection (F16)
100% 155
5.45 IPS
 
Object Detection (I8)
52% 384
13.5 IPS
 
Face Detection (F32)
100% 187
2.15 IPS
 
Face Detection (F16)
97% 231
2.66 IPS
 
Face Detection (I8)
40% 1397
16.1 IPS
 
Text Classification (F32)
54% 8
3.25 IPS
 
Text Classification (F16)
54% 8
3.23 IPS
 
Machine Translation (F32)
100% 98
15.1 IPS
 
Machine Translation (F16)
100% 97
15.0 IPS
 

Compare

Set Baseline Geekbench 6 now available