Geekbench AI Score

1995
Single Precision Score
2015
Half Precision Score
3046
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date April 13 2025 02:32 PM
Views 1

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 Ultra
Model IDsamsung SM-S928B
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% 1777
330.4 IPS
 
Image Classification (HP)
100% 1781
331.2 IPS
 
Image Classification (Q)
100% 2946
547.8 IPS
 
Image Segmentation (SP)
100% 1682
27.3 IPS
 
Image Segmentation (HP)
100% 2335
37.9 IPS
 
Image Segmentation (Q)
98% 2910
47.3 IPS
 
Pose Estimation (SP)
100% 3577
4.17 IPS
 
Pose Estimation (HP)
100% 3273
3.82 IPS
 
Pose Estimation (Q)
84% 6886
8.17 IPS
 
Object Detection (SP)
98% 1407
112.0 IPS
 
Object Detection (HP)
98% 1421
113.0 IPS
 
Object Detection (Q)
83% 1994
161.1 IPS
 
Face Detection (SP)
100% 2758
32.8 IPS
 
Face Detection (HP)
100% 2807
33.4 IPS
 
Face Detection (Q)
95% 4525
54.0 IPS
 
Depth Estimation (SP)
99% 2955
22.8 IPS
 
Depth Estimation (HP)
99% 2675
20.7 IPS
 
Depth Estimation (Q)
64% 4668
42.8 IPS
 
Style Transfer (SP)
89% 7493
9.73 IPS
 
Style Transfer (HP)
89% 7348
9.54 IPS
 
Style Transfer (Q)
98% 14163
18.3 IPS
 
Image Super-Resolution (SP)
100% 1355
50.0 IPS
 
Image Super-Resolution (HP)
100% 1339
49.4 IPS
 
Image Super-Resolution (Q)
97% 3417
126.6 IPS
 
Text Classification (SP)
100% 635
848.2 IPS
 
Text Classification (HP)
99% 632
844.0 IPS
 
Text Classification (Q)
88% 969
1.31 KIPS
 
Machine Translation (SP)
100% 1268
21.8 IPS
 
Machine Translation (HP)
100% 1227
21.1 IPS
 
Machine Translation (Q)
50% 590
20.9 IPS
 

Compare

Set Baseline Geekbench 6 now available