Geekbench ML Score

595
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date June 28 2025 08:44 AM
Views 1

System Information

System Information
Operating System Android 15
Model samsung SM-S918B
Model IDsamsung SM-S918B
Motherboard kalama
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3406 revision 0
Base Frequency 2.02 GHz
Cluster 13 Cores @ 2.02 GHz
Cluster 24 Cores @ 2.80 GHz
Cluster 31 Core @ 3.36 GHz
Memory Information
Size 10.79 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 579
62.0 IPS
 
Image Classification (F16)
100% 582
62.3 IPS
 
Image Classification (I8)
81% 218
23.3 IPS
 
Image Segmentation (F32)
100% 916
5.66 IPS
 
Image Segmentation (F16)
100% 924
5.71 IPS
 
Image Segmentation (I8)
89% 1111
6.86 IPS
 
Pose Estimation (F32)
100% 406
1.64 IPS
 
Pose Estimation (F16)
100% 388
1.57 IPS
 
Pose Estimation (I8)
80% 297
1.20 IPS
 
Object Detection (F32)
100% 630
22.1 IPS
 
Object Detection (F16)
100% 636
22.3 IPS
 
Object Detection (I8)
52% 380
13.3 IPS
 
Face Detection (F32)
100% 1015
11.7 IPS
 
Face Detection (F16)
100% 1008
11.6 IPS
 
Face Detection (I8)
75% 661
7.59 IPS
 
Text Classification (F32)
100% 367
145.0 IPS
 
Text Classification (F16)
100% 394
156.0 IPS
 
Machine Translation (F32)
100% 1076
165.9 IPS
 
Machine Translation (F16)
100% 1033
159.1 IPS
 

Compare

Set Baseline Geekbench 6 now available