Geekbench AI Score

3562
Single Precision Score
25111
Half Precision Score
46854
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date March 28 2025 01:52 PM
Views 2

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-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% 1634
303.9 IPS
 
Image Classification (HP)
100% 17223
3.20 KIPS
 
Image Classification (Q)
100% 32877
6.11 KIPS
 
Image Segmentation (SP)
100% 3052
49.5 IPS
 
Image Segmentation (HP)
97% 12457
202.7 IPS
 
Image Segmentation (Q)
96% 28382
461.9 IPS
 
Pose Estimation (SP)
100% 14127
16.5 IPS
 
Pose Estimation (HP)
100% 88074
102.8 IPS
 
Pose Estimation (Q)
97% 302849
354.6 IPS
 
Object Detection (SP)
100% 1589
126.0 IPS
 
Object Detection (HP)
100% 14028
1.11 KIPS
 
Object Detection (Q)
90% 23300
1.86 KIPS
 
Face Detection (SP)
100% 5133
61.0 IPS
 
Face Detection (HP)
100% 39809
473.0 IPS
 
Face Detection (Q)
97% 101158
1.21 KIPS
 
Depth Estimation (SP)
100% 5601
43.2 IPS
 
Depth Estimation (HP)
79% 56383
447.7 IPS
 
Depth Estimation (Q)
62% 106143
1.02 KIPS
 
Style Transfer (SP)
100% 29282
37.6 IPS
 
Style Transfer (HP)
99% 174507
224.3 IPS
 
Style Transfer (Q)
98% 261954
337.8 IPS
 
Image Super-Resolution (SP)
100% 4170
154.0 IPS
 
Image Super-Resolution (HP)
82% 22638
853.6 IPS
 
Image Super-Resolution (Q)
97% 59734
2.21 KIPS
 
Text Classification (SP)
100% 669
893.4 IPS
 
Text Classification (HP)
100% 7094
9.47 KIPS
 
Text Classification (Q)
93% 8424
11.3 KIPS
 
Machine Translation (SP)
100% 1253
21.6 IPS
 
Machine Translation (HP)
100% 5981
103.0 IPS
 
Machine Translation (Q)
56% 5472
140.4 IPS
 

Compare

Set Baseline Geekbench 6 now available