Geekbench AI Score

304
Single Precision Score
299
Half Precision Score
554
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date April 14 2025 03:53 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model realme RMX3938
Model IDrealme RMX3938
Motherboard ums9230_latte
Governoruscfreq
CPU Information
Name ARM ARMv8
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 2.69 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 168
31.3 IPS
 
Image Classification (HP)
100% 141
26.2 IPS
 
Image Classification (Q)
100% 437
81.2 IPS
 
Image Segmentation (SP)
100% 200
3.25 IPS
 
Image Segmentation (HP)
100% 201
3.26 IPS
 
Image Segmentation (Q)
98% 571
9.28 IPS
 
Pose Estimation (SP)
100% 695
0.81 IPS
 
Pose Estimation (HP)
100% 773
0.90 IPS
 
Pose Estimation (Q)
84% 1230
1.46 IPS
 
Object Detection (SP)
100% 183
14.5 IPS
 
Object Detection (HP)
100% 172
13.6 IPS
 
Object Detection (Q)
83% 347
28.0 IPS
 
Face Detection (SP)
100% 349
4.15 IPS
 
Face Detection (HP)
100% 370
4.39 IPS
 
Face Detection (Q)
95% 967
11.5 IPS
 
Depth Estimation (SP)
100% 468
3.61 IPS
 
Depth Estimation (HP)
99% 504
3.88 IPS
 
Depth Estimation (Q)
64% 947
8.68 IPS
 
Style Transfer (SP)
89% 1422
1.85 IPS
 
Style Transfer (HP)
89% 1458
1.89 IPS
 
Style Transfer (Q)
98% 2519
3.25 IPS
 
Image Super-Resolution (SP)
100% 242
8.95 IPS
 
Image Super-Resolution (HP)
100% 237
8.74 IPS
 
Image Super-Resolution (Q)
97% 626
23.2 IPS
 
Text Classification (SP)
100% 140
187.1 IPS
 
Text Classification (HP)
100% 123
164.8 IPS
 
Text Classification (Q)
88% 184
248.3 IPS
 
Machine Translation (SP)
100% 202
3.48 IPS
 
Machine Translation (HP)
100% 195
3.36 IPS
 
Machine Translation (Q)
50% 97
3.45 IPS
 

Compare

Set Baseline Geekbench 6 now available