Geekbench AI Score

1848
Single Precision Score
1848
Half Precision Score
3238
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

Upload Date November 24 2025 12:16 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 15
Model realme RMX5030
Model IDrealme RMX5030
Motherboard k6897v1_64
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3405 revision 0
Base Frequency 2.20 GHz
Cluster 14 Cores @ 2.20 GHz
Cluster 23 Cores @ 3.20 GHz
Cluster 31 Core @ 3.35 GHz
Memory Information
Size 11.22 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1392
258.8 IPS
 
Image Classification (HP)
100% 1435
266.8 IPS
 
Image Classification (Q)
100% 2160
401.7 IPS
 
Image Segmentation (SP)
100% 1394
22.6 IPS
 
Image Segmentation (HP)
100% 1518
24.6 IPS
 
Image Segmentation (Q)
98% 2707
44.0 IPS
 
Pose Estimation (SP)
100% 2591
3.02 IPS
 
Pose Estimation (HP)
100% 2563
2.99 IPS
 
Pose Estimation (Q)
84% 6301
7.47 IPS
 
Object Detection (SP)
98% 1337
106.4 IPS
 
Object Detection (HP)
98% 1340
106.6 IPS
 
Object Detection (Q)
83% 2238
180.8 IPS
 
Face Detection (SP)
100% 2818
33.5 IPS
 
Face Detection (HP)
100% 2762
32.8 IPS
 
Face Detection (Q)
95% 5443
65.0 IPS
 
Depth Estimation (SP)
99% 2511
19.4 IPS
 
Depth Estimation (HP)
99% 2360
18.2 IPS
 
Depth Estimation (Q)
64% 5235
47.9 IPS
 
Style Transfer (SP)
89% 6744
8.75 IPS
 
Style Transfer (HP)
89% 6659
8.64 IPS
 
Style Transfer (Q)
98% 13706
17.7 IPS
 
Image Super-Resolution (SP)
100% 1246
46.0 IPS
 
Image Super-Resolution (HP)
100% 1242
45.8 IPS
 
Image Super-Resolution (Q)
97% 3600
133.4 IPS
 
Text Classification (SP)
100% 771
1.03 KIPS
 
Text Classification (HP)
99% 775
1.03 KIPS
 
Text Classification (Q)
88% 1445
1.95 KIPS
 
Machine Translation (SP)
100% 1510
26.0 IPS
 
Machine Translation (HP)
100% 1490
25.7 IPS
 
Machine Translation (Q)
50% 758
26.9 IPS
 

Compare

Set Baseline Geekbench 6 now available