Geekbench ML Score

1678
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

User Beamish
Upload Date February 07 2026 01:13 AM
Views 5

System Information

System Information
Operating System Android 15
Model samsung SM-F711B
Model IDsamsung SM-F711B
Motherboard lahaina
Governorschedutil
CPU Information
Name ARM SM8350
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3396 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 7.22 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1311
140.5 IPS
 
Image Classification (F16)
100% 2049
219.6 IPS
 
Image Classification (I8)
80% 1853
198.5 IPS
 
Image Segmentation (F32)
100% 3187
19.7 IPS
 
Image Segmentation (F16)
100% 5106
31.5 IPS
 
Image Segmentation (I8)
89% 4995
30.9 IPS
 
Pose Estimation (F32)
100% 1531
6.19 IPS
 
Pose Estimation (F16)
100% 2825
11.4 IPS
 
Pose Estimation (I8)
80% 2797
11.3 IPS
 
Object Detection (F32)
100% 626
22.0 IPS
 
Object Detection (F16)
99% 737
25.9 IPS
 
Object Detection (I8)
53% 777
27.3 IPS
 
Face Detection (F32)
100% 2415
27.7 IPS
 
Face Detection (F16)
97% 4130
47.4 IPS
 
Face Detection (I8)
75% 3542
40.7 IPS
 
Text Classification (F32)
100% 787
311.2 IPS
 
Text Classification (F16)
98% 923
365.1 IPS
 
Machine Translation (F32)
100% 649
100.0 IPS
 
Machine Translation (F16)
100% 646
99.6 IPS
 

Compare

Set Baseline Geekbench 6 now available