Geekbench AI Score

2528
Single Precision Score
2544
Half Precision Score
3937
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 30 2024 06:07 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Samsung Exynos 2400
System Information
Operating System Android 14
Model Samsung Galaxy S24+
Model IDsamsung SM-S926B
Motherboard s5e9945
Governorenergy_aware
CPU Information
Name ARM ARMv8
Topology 1 Processor, 10 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3458 revision 1
Base Frequency 1.96 GHz
Cluster 14 Cores @ 1.96 GHz
Cluster 23 Cores @ 2.59 GHz
Cluster 32 Cores @ 2.90 GHz
Cluster 41 Core @ 3.21 GHz
Memory Information
Size 10.95 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2270
422.2 IPS
 
Image Classification (HP)
100% 2229
414.5 IPS
 
Image Classification (Q)
100% 3505
651.9 IPS
 
Image Segmentation (SP)
100% 2306
37.4 IPS
 
Image Segmentation (HP)
100% 2486
40.3 IPS
 
Image Segmentation (Q)
98% 4010
65.2 IPS
 
Pose Estimation (SP)
100% 3895
4.55 IPS
 
Pose Estimation (HP)
100% 3880
4.53 IPS
 
Pose Estimation (Q)
84% 8867
10.5 IPS
 
Object Detection (SP)
98% 1950
155.2 IPS
 
Object Detection (HP)
98% 2010
159.9 IPS
 
Object Detection (Q)
83% 3123
252.2 IPS
 
Face Detection (SP)
100% 3949
46.9 IPS
 
Face Detection (HP)
100% 3729
44.3 IPS
 
Face Detection (Q)
95% 6524
77.9 IPS
 
Depth Estimation (SP)
99% 3898
30.1 IPS
 
Depth Estimation (HP)
99% 3917
30.3 IPS
 
Depth Estimation (Q)
64% 6592
60.4 IPS
 
Style Transfer (SP)
89% 9585
12.4 IPS
 
Style Transfer (HP)
89% 9241
12.0 IPS
 
Style Transfer (Q)
98% 16179
20.9 IPS
 
Image Super-Resolution (SP)
100% 1746
64.5 IPS
 
Image Super-Resolution (HP)
100% 1814
67.0 IPS
 
Image Super-Resolution (Q)
97% 3845
142.5 IPS
 
Text Classification (SP)
100% 647
863.8 IPS
 
Text Classification (HP)
99% 677
903.8 IPS
 
Text Classification (Q)
88% 1091
1.47 KIPS
 
Machine Translation (SP)
100% 1609
27.7 IPS
 
Machine Translation (HP)
100% 1588
27.4 IPS
 
Machine Translation (Q)
50% 788
28.0 IPS
 

Compare

Set Baseline Geekbench 6 now available