Geekbench AI Score

1304
Single Precision Score
1922
Half Precision Score
1436
Quantized Score
Geekbench AI 1.6.1 for Android AArch64

Result Information

User Lazerdude
Upload Date January 16 2026 01:58 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device ARM ARMv8
System Information
Operating System Android 15
Model SHARP SH-M30
Model IDSHARP SH-M30
Motherboard Mikazuki
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3458 revision 1
Base Frequency 2.02 GHz
Cluster 13 Cores @ 2.02 GHz
Cluster 24 Cores @ 2.80 GHz
Cluster 31 Core @ 3.01 GHz
Memory Information
Size 11.09 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 884
164.3 IPS
 
Image Classification (HP)
100% 1233
229.3 IPS
 
Image Classification (Q)
100% 1143
212.5 IPS
 
Image Segmentation (SP)
100% 1768
28.7 IPS
 
Image Segmentation (HP)
100% 2832
45.9 IPS
 
Image Segmentation (Q)
98% 2000
32.5 IPS
 
Pose Estimation (SP)
100% 6874
8.02 IPS
 
Pose Estimation (HP)
99% 12185
14.3 IPS
 
Pose Estimation (Q)
96% 11748
13.8 IPS
 
Object Detection (SP)
100% 659
52.3 IPS
 
Object Detection (HP)
99% 911
72.3 IPS
 
Object Detection (Q)
87% 858
68.9 IPS
 
Face Detection (SP)
100% 2707
32.2 IPS
 
Face Detection (HP)
100% 4208
50.0 IPS
 
Face Detection (Q)
97% 3149
37.5 IPS
 
Depth Estimation (SP)
100% 3618
27.9 IPS
 
Depth Estimation (HP)
98% 5403
41.8 IPS
 
Depth Estimation (Q)
61% 4069
40.1 IPS
 
Style Transfer (SP)
100% 8392
10.8 IPS
 
Style Transfer (HP)
100% 16215
20.8 IPS
 
Style Transfer (Q)
98% 15702
20.2 IPS
 
Image Super-Resolution (SP)
100% 1534
56.6 IPS
 
Image Super-Resolution (HP)
100% 2210
81.6 IPS
 
Image Super-Resolution (Q)
97% 2135
79.1 IPS
 
Text Classification (SP)
35% 37
360.2 IPS
 
Text Classification (HP)
35% 46
421.9 IPS
 
Text Classification (Q)
33% 29
350.1 IPS
 
Machine Translation (SP)
100% 432
7.43 IPS
 
Machine Translation (HP)
97% 475
8.21 IPS
 
Machine Translation (Q)
43% 130
7.38 IPS
 

Compare

Set Baseline Geekbench 6 now available