Geekbench AI Score

2692
Single Precision Score
2701
Half Precision Score
4285
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 26 2024 08:14 AM
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% 1964
365.3 IPS
 
Image Classification (HP)
100% 2286
425.1 IPS
 
Image Classification (Q)
100% 3498
650.6 IPS
 
Image Segmentation (SP)
100% 2567
41.6 IPS
 
Image Segmentation (HP)
100% 2537
41.1 IPS
 
Image Segmentation (Q)
98% 3966
64.5 IPS
 
Pose Estimation (SP)
100% 4047
4.72 IPS
 
Pose Estimation (HP)
100% 3972
4.64 IPS
 
Pose Estimation (Q)
84% 8931
10.6 IPS
 
Object Detection (SP)
98% 2009
159.9 IPS
 
Object Detection (HP)
98% 2025
161.1 IPS
 
Object Detection (Q)
83% 2691
217.4 IPS
 
Face Detection (SP)
100% 4055
48.2 IPS
 
Face Detection (HP)
100% 4034
47.9 IPS
 
Face Detection (Q)
95% 7320
87.4 IPS
 
Depth Estimation (SP)
99% 3753
29.0 IPS
 
Depth Estimation (HP)
99% 3885
30.0 IPS
 
Depth Estimation (Q)
64% 6965
63.8 IPS
 
Style Transfer (SP)
89% 9827
12.8 IPS
 
Style Transfer (HP)
89% 10002
13.0 IPS
 
Style Transfer (Q)
98% 19947
25.7 IPS
 
Image Super-Resolution (SP)
100% 2117
78.2 IPS
 
Image Super-Resolution (HP)
100% 2091
77.2 IPS
 
Image Super-Resolution (Q)
97% 4831
179.0 IPS
 
Text Classification (SP)
100% 894
1.19 KIPS
 
Text Classification (HP)
99% 804
1.07 KIPS
 
Text Classification (Q)
88% 1497
2.02 KIPS
 
Machine Translation (SP)
100% 1726
29.7 IPS
 
Machine Translation (HP)
100% 1682
29.0 IPS
 
Machine Translation (Q)
50% 852
30.2 IPS
 

Compare

Set Baseline Geekbench 6 now available