Geekbench AI Score

131
Single Precision Score
176
Half Precision Score
170
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date October 28 2024 05:09 AM
Views 9

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device Samsung Exynos 9611
System Information
Operating System Android 13
Model Samsung Galaxy Tab S6 Lite
Model IDsamsung SM-P610
Motherboard exynos9611
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3337 revision 2
Base Frequency 1.74 GHz
Cluster 14 Cores @ 1.74 GHz
Cluster 24 Cores @ 2.31 GHz
Memory Information
Size 3.62 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 107
19.9 IPS
 
Image Classification (HP)
100% 172
32.0 IPS
 
Image Classification (Q)
99% 165
30.8 IPS
 
Image Segmentation (SP)
100% 116
1.89 IPS
 
Image Segmentation (HP)
100% 158
2.56 IPS
 
Image Segmentation (Q)
98% 156
2.54 IPS
 
Pose Estimation (SP)
100% 76
0.09 IPS
 
Pose Estimation (HP)
100% 109
0.13 IPS
 
Pose Estimation (Q)
96% 109
0.13 IPS
 
Object Detection (SP)
100% 86
6.78 IPS
 
Object Detection (HP)
100% 152
12.0 IPS
 
Object Detection (Q)
83% 146
11.8 IPS
 
Face Detection (SP)
100% 346
4.11 IPS
 
Face Detection (HP)
100% 456
5.42 IPS
 
Face Detection (Q)
97% 429
5.11 IPS
 
Depth Estimation (SP)
100% 178
1.37 IPS
 
Depth Estimation (HP)
99% 194
1.49 IPS
 
Depth Estimation (Q)
62% 201
1.90 IPS
 
Style Transfer (SP)
100% 333
0.43 IPS
 
Style Transfer (HP)
100% 549
0.71 IPS
 
Style Transfer (Q)
98% 458
0.59 IPS
 
Image Super-Resolution (SP)
100% 117
4.34 IPS
 
Image Super-Resolution (HP)
100% 180
6.63 IPS
 
Image Super-Resolution (Q)
97% 175
6.50 IPS
 
Text Classification (SP)
100% 66
88.0 IPS
 
Text Classification (HP)
100% 66
87.7 IPS
 
Text Classification (Q)
91% 86
116.1 IPS
 
Machine Translation (SP)
100% 116
1.99 IPS
 
Machine Translation (HP)
100% 115
1.97 IPS
 
Machine Translation (Q)
57% 87
2.13 IPS
 

Compare

Set Baseline Geekbench 6 now available