Geekbench AI Score

2922
Single Precision Score
11364
Half Precision Score
22763
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

User wudi890
Upload Date September 09 2024 08:45 PM
Views 29

System Information

AI Information
Framework TensorFlow Lite
Backend ENN
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% 1390
258.4 IPS
 
Image Classification (HP)
100% 8636
1.61 KIPS
 
Image Classification (Q)
100% 26326
4.90 KIPS
 
Image Segmentation (SP)
100% 2368
38.4 IPS
 
Image Segmentation (HP)
78% 7343
123.0 IPS
 
Image Segmentation (Q)
95% 27617
449.8 IPS
 
Pose Estimation (SP)
100% 13793
16.1 IPS
 
Pose Estimation (HP)
100% 84406
98.5 IPS
 
Pose Estimation (Q)
78% 286027
345.8 IPS
 
Object Detection (SP)
100% 1575
124.9 IPS
 
Object Detection (HP)
100% 7510
595.7 IPS
 
Object Detection (Q)
90% 12520
1.00 KIPS
 
Face Detection (SP)
100% 3935
46.8 IPS
 
Face Detection (HP)
100% 20972
249.2 IPS
 
Face Detection (Q)
96% 53063
633.0 IPS
 
Depth Estimation (SP)
100% 5133
39.5 IPS
 
Depth Estimation (HP)
79% 45994
365.3 IPS
 
Depth Estimation (Q)
63% 80471
745.2 IPS
 
Style Transfer (SP)
100% 14644
18.8 IPS
 
Style Transfer (HP)
99% 140654
180.8 IPS
 
Style Transfer (Q)
98% 244843
315.8 IPS
 
Image Super-Resolution (SP)
100% 3880
143.3 IPS
 
Image Super-Resolution (HP)
82% 15720
593.3 IPS
 
Image Super-Resolution (Q)
83% 29573
1.11 KIPS
 
Text Classification (SP)
100% 464
618.7 IPS
 
Text Classification (HP)
100% 457
609.7 IPS
 
Text Classification (Q)
91% 745
1.00 KIPS
 
Machine Translation (SP)
100% 1194
20.6 IPS
 
Machine Translation (HP)
99% 917
15.8 IPS
 
Machine Translation (Q)
59% 623
14.3 IPS
 

Compare

Set Baseline Geekbench 6 now available