Geekbench ML Score

1079
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date September 28 2025 04:09 PM
Views 4

System Information

System Information
Operating System Android 15
Model samsung SM-X910
Model IDsamsung SM-X910
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 10.92 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 554
103.7 IPS
 
Image Classification (F16)
100% 548
102.6 IPS
 
Image Classification (I8)
97% 899
168.1 IPS
 
Image Segmentation (F32)
100% 693
11.6 IPS
 
Image Segmentation (F16)
100% 677
11.3 IPS
 
Image Segmentation (I8)
98% 835
13.9 IPS
 
Pose Estimation (F32)
100% 1274
1.54 IPS
 
Pose Estimation (F16)
100% 1257
1.52 IPS
 
Pose Estimation (I8)
100% 5240
6.35 IPS
 
Object Detection (F32)
100% 568
42.4 IPS
 
Object Detection (F16)
100% 566
42.3 IPS
 
Object Detection (I8)
61% 1178
87.9 IPS
 
Face Detection (F32)
100% 1169
13.9 IPS
 
Face Detection (F16)
100% 1113
13.2 IPS
 
Face Detection (I8)
86% 1915
22.8 IPS
 
Depth Estimation (F32)
100% 1243
9.64 IPS
 
Depth Estimation (F16)
100% 1239
9.61 IPS
 
Depth Estimation (I8)
95% 2340
18.1 IPS
 
Style Transfer (F32)
100% 2258
2.97 IPS
 
Style Transfer (F16)
100% 2261
2.97 IPS
 
Style Transfer (I8)
98% 4421
5.82 IPS
 
Image Super-Resolution (F32)
100% 822
29.4 IPS
 
Image Super-Resolution (F16)
100% 822
29.4 IPS
 
Image Super-Resolution (I8)
98% 2229
79.6 IPS
 
Text Classification (F32)
100% 629
903.7 IPS
 
Text Classification (F16)
100% 602
865.4 IPS
 
Text Classification (I8)
92% 397
569.9 IPS
 
Machine Translation (F32)
100% 1238
22.8 IPS
 
Machine Translation (F16)
100% 1221
22.5 IPS
 
Machine Translation (I8)
64% 426
7.85 IPS
 

Compare

Set Baseline Geekbench 6 now available