Geekbench AI Score

2134
Single Precision Score
2138
Half Precision Score
3117
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 18 2024 01:56 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-S926N
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% 1778
330.7 IPS
 
Image Classification (HP)
100% 2102
390.9 IPS
 
Image Classification (Q)
100% 3097
575.9 IPS
 
Image Segmentation (SP)
100% 2225
36.1 IPS
 
Image Segmentation (HP)
100% 2032
32.9 IPS
 
Image Segmentation (Q)
98% 3906
63.5 IPS
 
Pose Estimation (SP)
100% 3616
4.22 IPS
 
Pose Estimation (HP)
100% 3691
4.31 IPS
 
Pose Estimation (Q)
84% 6450
7.65 IPS
 
Object Detection (SP)
98% 1355
107.9 IPS
 
Object Detection (HP)
98% 1357
108.0 IPS
 
Object Detection (Q)
83% 2098
169.5 IPS
 
Face Detection (SP)
100% 3191
37.9 IPS
 
Face Detection (HP)
100% 3189
37.9 IPS
 
Face Detection (Q)
95% 4401
52.5 IPS
 
Depth Estimation (SP)
99% 3060
23.6 IPS
 
Depth Estimation (HP)
99% 3199
24.7 IPS
 
Depth Estimation (Q)
64% 4789
43.9 IPS
 
Style Transfer (SP)
89% 8100
10.5 IPS
 
Style Transfer (HP)
89% 8216
10.7 IPS
 
Style Transfer (Q)
98% 14919
19.2 IPS
 
Image Super-Resolution (SP)
100% 1786
66.0 IPS
 
Image Super-Resolution (HP)
100% 1639
60.5 IPS
 
Image Super-Resolution (Q)
97% 3227
119.6 IPS
 
Text Classification (SP)
100% 556
742.4 IPS
 
Text Classification (HP)
99% 567
757.3 IPS
 
Text Classification (Q)
88% 817
1.10 KIPS
 
Machine Translation (SP)
100% 1290
22.2 IPS
 
Machine Translation (HP)
100% 1200
20.7 IPS
 
Machine Translation (Q)
50% 639
22.7 IPS
 

Compare

Set Baseline Geekbench 6 now available