Geekbench AI Score

2597
Single Precision Score
2649
Half Precision Score
4263
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 26 2024 09:43 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% 1868
347.3 IPS
 
Image Classification (HP)
100% 1879
349.4 IPS
 
Image Classification (Q)
100% 2983
554.7 IPS
 
Image Segmentation (SP)
100% 2168
35.2 IPS
 
Image Segmentation (HP)
100% 2514
40.8 IPS
 
Image Segmentation (Q)
98% 3930
63.9 IPS
 
Pose Estimation (SP)
100% 4119
4.81 IPS
 
Pose Estimation (HP)
100% 4022
4.69 IPS
 
Pose Estimation (Q)
84% 8940
10.6 IPS
 
Object Detection (SP)
98% 1948
155.0 IPS
 
Object Detection (HP)
98% 2033
161.8 IPS
 
Object Detection (Q)
83% 3180
256.9 IPS
 
Face Detection (SP)
100% 3881
46.1 IPS
 
Face Detection (HP)
100% 4003
47.6 IPS
 
Face Detection (Q)
95% 7370
88.0 IPS
 
Depth Estimation (SP)
99% 3607
27.9 IPS
 
Depth Estimation (HP)
99% 3597
27.8 IPS
 
Depth Estimation (Q)
64% 6483
59.4 IPS
 
Style Transfer (SP)
89% 9906
12.9 IPS
 
Style Transfer (HP)
89% 10034
13.0 IPS
 
Style Transfer (Q)
98% 18869
24.3 IPS
 
Image Super-Resolution (SP)
100% 2049
75.7 IPS
 
Image Super-Resolution (HP)
100% 2067
76.3 IPS
 
Image Super-Resolution (Q)
97% 5009
185.6 IPS
 
Text Classification (SP)
100% 885
1.18 KIPS
 
Text Classification (HP)
99% 872
1.16 KIPS
 
Text Classification (Q)
88% 1524
2.06 KIPS
 
Machine Translation (SP)
100% 1711
29.5 IPS
 
Machine Translation (HP)
100% 1697
29.2 IPS
 
Machine Translation (Q)
50% 866
30.8 IPS
 

Compare

Set Baseline Geekbench 6 now available