Geekbench ML Score

1536
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 11 2025 05:46 PM
Views 1

System Information

System Information
Operating System Android 15
Model realme RMX3301
Model IDrealme RMX3301
Motherboard taro
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.50 GHz
Cluster 31 Core @ 3.00 GHz
Memory Information
Size 10.95 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1121
120.1 IPS
 
Image Classification (F16)
100% 1384
148.3 IPS
 
Image Classification (I8)
80% 1424
152.6 IPS
 
Image Segmentation (F32)
100% 3829
23.6 IPS
 
Image Segmentation (F16)
100% 5385
33.3 IPS
 
Image Segmentation (I8)
89% 4793
29.6 IPS
 
Pose Estimation (F32)
100% 1955
7.91 IPS
 
Pose Estimation (F16)
100% 3694
14.9 IPS
 
Pose Estimation (I8)
80% 3673
14.9 IPS
 
Object Detection (F32)
100% 612
21.5 IPS
 
Object Detection (F16)
99% 693
24.3 IPS
 
Object Detection (I8)
53% 689
24.2 IPS
 
Face Detection (F32)
100% 2214
25.4 IPS
 
Face Detection (F16)
97% 3252
37.4 IPS
 
Face Detection (I8)
75% 2523
29.0 IPS
 
Text Classification (F32)
100% 365
144.2 IPS
 
Text Classification (F16)
98% 414
163.6 IPS
 
Machine Translation (F32)
100% 852
131.3 IPS
 
Machine Translation (F16)
100% 883
136.1 IPS
 

Compare

Set Baseline Geekbench 6 now available