Geekbench AI Score

131
Single Precision Score
144
Half Precision Score
153
Quantized Score
Geekbench AI 1.0.0 for Android AArch64

Result Information

Upload Date August 17 2024 04:56 PM
Views 10

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device ARM ARMv8
System Information
Operating System Android 14
Model realme RMX3939
Model IDrealme RMX3939
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 3.67 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 78
14.6 IPS
 
Image Classification (HP)
100% 120
22.4 IPS
 
Image Classification (Q)
99% 103
19.1 IPS
 
Image Segmentation (SP)
100% 106
1.72 IPS
 
Image Segmentation (HP)
100% 160
2.59 IPS
 
Image Segmentation (Q)
98% 144
2.35 IPS
 
Pose Estimation (SP)
100% 469
0.55 IPS
 
Pose Estimation (HP)
100% 259
0.30 IPS
 
Pose Estimation (Q)
96% 432
0.51 IPS
 
Object Detection (SP)
100% 44
3.49 IPS
 
Object Detection (HP)
100% 44
3.49 IPS
 
Object Detection (Q)
89% 88
7.07 IPS
 
Face Detection (SP)
100% 268
3.18 IPS
 
Face Detection (HP)
100% 321
3.82 IPS
 
Face Detection (Q)
97% 202
2.41 IPS
 
Depth Estimation (SP)
100% 367
2.83 IPS
 
Depth Estimation (HP)
98% 288
2.23 IPS
 
Depth Estimation (Q)
83% 385
3.02 IPS
 
Style Transfer (SP)
100% 335
0.43 IPS
 
Style Transfer (HP)
100% 196
0.25 IPS
 
Style Transfer (Q)
98% 615
0.79 IPS
 
Image Super-Resolution (SP)
100% 206
7.61 IPS
 
Image Super-Resolution (HP)
100% 149
5.49 IPS
 
Image Super-Resolution (Q)
97% 213
7.88 IPS
 
Text Classification (SP)
100% 18
24.3 IPS
 
Text Classification (HP)
100% 63
83.9 IPS
 
Text Classification (Q)
93% 24
32.2 IPS
 
Machine Translation (SP)
100% 73
1.26 IPS
 
Machine Translation (HP)
100% 107
1.85 IPS
 
Machine Translation (Q)
55% 53
1.40 IPS
 

Compare

Set Baseline Geekbench 6 now available