Geekbench AI Score

2138
Single Precision Score
2174
Half Precision Score
3118
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 19 2024 08:04 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% 1769
329.1 IPS
 
Image Classification (HP)
100% 2147
399.3 IPS
 
Image Classification (Q)
100% 3214
597.7 IPS
 
Image Segmentation (SP)
100% 2321
37.6 IPS
 
Image Segmentation (HP)
100% 2408
39.0 IPS
 
Image Segmentation (Q)
98% 3909
63.6 IPS
 
Pose Estimation (SP)
100% 3613
4.22 IPS
 
Pose Estimation (HP)
100% 3520
4.11 IPS
 
Pose Estimation (Q)
84% 6493
7.70 IPS
 
Object Detection (SP)
98% 1370
109.0 IPS
 
Object Detection (HP)
98% 1370
109.0 IPS
 
Object Detection (Q)
83% 2127
171.8 IPS
 
Face Detection (SP)
100% 3268
38.8 IPS
 
Face Detection (HP)
100% 3282
39.0 IPS
 
Face Detection (Q)
95% 4442
53.0 IPS
 
Depth Estimation (SP)
99% 3131
24.2 IPS
 
Depth Estimation (HP)
99% 3075
23.8 IPS
 
Depth Estimation (Q)
64% 4540
41.6 IPS
 
Style Transfer (SP)
89% 7571
9.83 IPS
 
Style Transfer (HP)
89% 7517
9.76 IPS
 
Style Transfer (Q)
98% 13571
17.5 IPS
 
Image Super-Resolution (SP)
100% 1559
57.6 IPS
 
Image Super-Resolution (HP)
100% 1584
58.5 IPS
 
Image Super-Resolution (Q)
97% 3259
120.7 IPS
 
Text Classification (SP)
100% 559
745.9 IPS
 
Text Classification (HP)
99% 595
793.6 IPS
 
Text Classification (Q)
88% 905
1.22 KIPS
 
Machine Translation (SP)
100% 1457
25.1 IPS
 
Machine Translation (HP)
100% 1324
22.8 IPS
 
Machine Translation (Q)
50% 621
22.1 IPS
 

Compare

Set Baseline Geekbench 6 now available