Geekbench AI Score

160
Single Precision Score
218
Half Precision Score
216
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date January 29 2025 07:18 PM
Views 52

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM ARMv8
System Information
Operating System Android 15
Model realme RMX3943
Model IDrealme RMX3943
Motherboard k6835v2_64
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.40 GHz
Memory Information
Size 7.45 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 101
18.8 IPS
 
Image Classification (HP)
100% 174
32.4 IPS
 
Image Classification (Q)
99% 165
30.7 IPS
 
Image Segmentation (SP)
100% 144
2.33 IPS
 
Image Segmentation (HP)
100% 250
4.05 IPS
 
Image Segmentation (Q)
98% 243
3.95 IPS
 
Pose Estimation (SP)
100% 97
0.11 IPS
 
Pose Estimation (HP)
100% 116
0.14 IPS
 
Pose Estimation (Q)
96% 116
0.14 IPS
 
Object Detection (SP)
100% 80
6.38 IPS
 
Object Detection (HP)
100% 125
9.94 IPS
 
Object Detection (Q)
83% 121
9.81 IPS
 
Face Detection (SP)
100% 308
3.65 IPS
 
Face Detection (HP)
100% 428
5.08 IPS
 
Face Detection (Q)
97% 429
5.12 IPS
 
Depth Estimation (SP)
100% 186
1.43 IPS
 
Depth Estimation (HP)
99% 244
1.88 IPS
 
Depth Estimation (Q)
62% 197
1.87 IPS
 
Style Transfer (SP)
100% 370
0.48 IPS
 
Style Transfer (HP)
100% 522
0.67 IPS
 
Style Transfer (Q)
98% 520
0.67 IPS
 
Image Super-Resolution (SP)
100% 94
3.49 IPS
 
Image Super-Resolution (HP)
100% 143
5.30 IPS
 
Image Super-Resolution (Q)
97% 142
5.25 IPS
 
Text Classification (SP)
100% 171
228.6 IPS
 
Text Classification (HP)
100% 171
228.1 IPS
 
Text Classification (Q)
91% 278
373.7 IPS
 
Machine Translation (SP)
100% 288
4.96 IPS
 
Machine Translation (HP)
100% 289
4.98 IPS
 
Machine Translation (Q)
57% 227
5.54 IPS
 

Compare

Set Baseline Geekbench 6 now available