Geekbench AI Score

2729
Single Precision Score
2720
Half Precision Score
4171
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 19 2024 08:13 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-S921B
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 7.06 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2313
430.2 IPS
 
Image Classification (HP)
100% 2291
426.1 IPS
 
Image Classification (Q)
100% 3276
609.3 IPS
 
Image Segmentation (SP)
100% 2502
40.6 IPS
 
Image Segmentation (HP)
100% 2546
41.3 IPS
 
Image Segmentation (Q)
98% 3943
64.1 IPS
 
Pose Estimation (SP)
100% 4141
4.83 IPS
 
Pose Estimation (HP)
100% 4015
4.69 IPS
 
Pose Estimation (Q)
84% 8841
10.5 IPS
 
Object Detection (SP)
98% 2041
162.4 IPS
 
Object Detection (HP)
98% 2045
162.7 IPS
 
Object Detection (Q)
83% 3035
245.2 IPS
 
Face Detection (SP)
100% 4026
47.8 IPS
 
Face Detection (HP)
100% 4043
48.0 IPS
 
Face Detection (Q)
95% 7209
86.1 IPS
 
Depth Estimation (SP)
99% 3936
30.4 IPS
 
Depth Estimation (HP)
99% 3937
30.4 IPS
 
Depth Estimation (Q)
64% 6567
60.1 IPS
 
Style Transfer (SP)
89% 9749
12.7 IPS
 
Style Transfer (HP)
89% 9635
12.5 IPS
 
Style Transfer (Q)
98% 19040
24.6 IPS
 
Image Super-Resolution (SP)
100% 2107
77.8 IPS
 
Image Super-Resolution (HP)
100% 2145
79.2 IPS
 
Image Super-Resolution (Q)
97% 4847
179.6 IPS
 
Text Classification (SP)
100% 826
1.10 KIPS
 
Text Classification (HP)
99% 856
1.14 KIPS
 
Text Classification (Q)
88% 1209
1.63 KIPS
 
Machine Translation (SP)
100% 1744
30.0 IPS
 
Machine Translation (HP)
100% 1644
28.3 IPS
 
Machine Translation (Q)
50% 871
30.9 IPS
 

Compare

Set Baseline Geekbench 6 now available