Geekbench AI Score

398
Single Precision Score
398
Half Precision Score
735
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date November 17 2024 10:04 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM Unisoc
System Information
Operating System Android 13
Model realme RMX3834
Model IDrealme RMX3834
Motherboard ums9230_hulk
Governorschedutil
CPU Information
Name ARM Unisoc
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 3 part 3338 revision 1
Base Frequency 1.82 GHz
Cluster 18 Cores @ 1.82 GHz
Memory Information
Size 2.70 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 197
36.6 IPS
 
Image Classification (HP)
100% 201
37.3 IPS
 
Image Classification (Q)
100% 546
101.5 IPS
 
Image Segmentation (SP)
100% 245
3.98 IPS
 
Image Segmentation (HP)
100% 242
3.93 IPS
 
Image Segmentation (Q)
98% 671
10.9 IPS
 
Pose Estimation (SP)
100% 872
1.02 IPS
 
Pose Estimation (HP)
100% 886
1.03 IPS
 
Pose Estimation (Q)
84% 1506
1.79 IPS
 
Object Detection (SP)
100% 221
17.5 IPS
 
Object Detection (HP)
100% 214
17.0 IPS
 
Object Detection (Q)
83% 518
41.9 IPS
 
Face Detection (SP)
100% 487
5.78 IPS
 
Face Detection (HP)
100% 490
5.83 IPS
 
Face Detection (Q)
95% 1258
15.0 IPS
 
Depth Estimation (SP)
100% 657
5.06 IPS
 
Depth Estimation (HP)
99% 677
5.22 IPS
 
Depth Estimation (Q)
64% 1341
12.3 IPS
 
Style Transfer (SP)
89% 1769
2.30 IPS
 
Style Transfer (HP)
89% 1757
2.28 IPS
 
Style Transfer (Q)
98% 3449
4.45 IPS
 
Image Super-Resolution (SP)
100% 328
12.1 IPS
 
Image Super-Resolution (HP)
100% 338
12.5 IPS
 
Image Super-Resolution (Q)
97% 796
29.5 IPS
 
Text Classification (SP)
100% 194
258.5 IPS
 
Text Classification (HP)
100% 188
250.9 IPS
 
Text Classification (Q)
88% 240
324.2 IPS
 
Machine Translation (SP)
100% 302
5.20 IPS
 
Machine Translation (HP)
100% 293
5.04 IPS
 
Machine Translation (Q)
50% 145
5.16 IPS
 

Compare

Set Baseline Geekbench 6 now available