Geekbench ML Score

1102
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

User Beamish
Upload Date December 12 2025 08:14 PM
Views 4

System Information

System Information
Operating System Android 13
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% 1022
109.5 IPS
 
Image Classification (F16)
100% 1424
152.6 IPS
 
Image Classification (I8)
80% 1266
135.7 IPS
 
Image Segmentation (F32)
100% 2390
14.8 IPS
 
Image Segmentation (F16)
100% 3851
23.8 IPS
 
Image Segmentation (I8)
89% 3563
22.0 IPS
 
Pose Estimation (F32)
100% 945
3.82 IPS
 
Pose Estimation (F16)
100% 1786
7.23 IPS
 
Pose Estimation (I8)
80% 1655
6.69 IPS
 
Object Detection (F32)
100% 342
12.0 IPS
 
Object Detection (F16)
99% 451
15.8 IPS
 
Object Detection (I8)
53% 449
15.8 IPS
 
Face Detection (F32)
100% 1428
16.4 IPS
 
Face Detection (F16)
97% 2598
29.8 IPS
 
Face Detection (I8)
75% 2293
26.3 IPS
 
Text Classification (F32)
100% 485
191.7 IPS
 
Text Classification (F16)
98% 600
237.4 IPS
 
Machine Translation (F32)
100% 468
72.2 IPS
 
Machine Translation (F16)
100% 469
72.3 IPS
 

Compare

Set Baseline Geekbench 6 now available