Geekbench AI Score

2172
Single Precision Score
2399
Half Precision Score
3470
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 21 2024 03:12 PM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Qualcomm Snapdragon 8 Gen 3
System Information
Operating System Android 15
Model Samsung Galaxy S24+
Model IDsamsung SM-S926U
Motherboard pineapple
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 2.26 GHz
Cluster 12 Cores @ 2.27 GHz
Cluster 22 Cores @ 2.96 GHz
Cluster 33 Cores @ 3.15 GHz
Cluster 41 Core @ 3.40 GHz
Memory Information
Size 10.83 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1451
269.8 IPS
 
Image Classification (HP)
100% 1954
363.4 IPS
 
Image Classification (Q)
100% 1752
325.8 IPS
 
Image Segmentation (SP)
100% 1987
32.2 IPS
 
Image Segmentation (HP)
100% 2193
35.6 IPS
 
Image Segmentation (Q)
98% 3533
57.5 IPS
 
Pose Estimation (SP)
100% 3612
4.21 IPS
 
Pose Estimation (HP)
100% 3579
4.18 IPS
 
Pose Estimation (Q)
84% 8308
9.85 IPS
 
Object Detection (SP)
98% 1684
134.0 IPS
 
Object Detection (HP)
98% 1643
130.8 IPS
 
Object Detection (Q)
83% 2094
169.2 IPS
 
Face Detection (SP)
100% 2392
28.4 IPS
 
Face Detection (HP)
100% 3244
38.6 IPS
 
Face Detection (Q)
95% 5708
68.1 IPS
 
Depth Estimation (SP)
99% 3237
25.0 IPS
 
Depth Estimation (HP)
99% 3415
26.4 IPS
 
Depth Estimation (Q)
64% 5779
52.9 IPS
 
Style Transfer (SP)
89% 8550
11.1 IPS
 
Style Transfer (HP)
89% 8497
11.0 IPS
 
Style Transfer (Q)
98% 13559
17.5 IPS
 
Image Super-Resolution (SP)
100% 1587
58.6 IPS
 
Image Super-Resolution (HP)
100% 1866
68.9 IPS
 
Image Super-Resolution (Q)
97% 4974
184.3 IPS
 
Text Classification (SP)
100% 844
1.13 KIPS
 
Text Classification (HP)
99% 915
1.22 KIPS
 
Text Classification (Q)
88% 1399
1.89 KIPS
 
Machine Translation (SP)
100% 1503
25.9 IPS
 
Machine Translation (HP)
100% 1560
26.9 IPS
 
Machine Translation (Q)
50% 757
26.9 IPS
 

Compare

Set Baseline Geekbench 6 now available