Geekbench ML Score

627
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

User almaspite
Upload Date March 28 2026 12:32 PM
Views 6

System Information

System Information
Operating System Android 9
Model Samsung Galaxy Note 8
Model IDsamsung SM-N950F
Motherboard universal8895
Governorinteractive
CPU Information
Name ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 83 architecture 8 variant 4 part 1 revision 0
Base Frequency 1.69 GHz
Cluster 14 Cores @ 1.69 GHz
Cluster 24 Cores @ 2.31 GHz
Memory Information
Size 5.21 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 490
52.6 IPS
 
Image Classification (F16)
100% 844
90.4 IPS
 
Image Classification (I8)
81% 801
85.8 IPS
 
Image Segmentation (F32)
100% 1208
7.46 IPS
 
Image Segmentation (F16)
100% 2578
15.9 IPS
 
Image Segmentation (I8)
89% 2461
15.2 IPS
 
Pose Estimation (F32)
100% 257
1.04 IPS
 
Pose Estimation (F16)
0% 977
3.95 IPS
 
Pose Estimation (I8)
0% 983
3.98 IPS
 
Object Detection (F32)
100% 214
7.49 IPS
 
Object Detection (F16)
99% 251
8.82 IPS
 
Object Detection (I8)
54% 244
8.55 IPS
 
Face Detection (F32)
100% 1089
12.5 IPS
 
Face Detection (F16)
97% 2085
24.0 IPS
 
Face Detection (I8)
75% 1791
20.6 IPS
 
Text Classification (F32)
100% 548
216.8 IPS
 
Text Classification (F16)
98% 630
249.3 IPS
 
Machine Translation (F32)
100% 110
17.0 IPS
 
Machine Translation (F16)
100% 111
17.2 IPS
 

Compare

Set Baseline Geekbench 6 now available