Geekbench AI Score

310
Single Precision Score
329
Half Precision Score
1041
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date December 30 2024 10:37 PM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device Samsung Exynos 2400
System Information
Operating System Android 15
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 10.94 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 277
51.5 IPS
 
Image Classification (HP)
100% 279
51.8 IPS
 
Image Classification (Q)
99% 711
132.6 IPS
 
Image Segmentation (SP)
100% 767
12.4 IPS
 
Image Segmentation (HP)
100% 1260
20.4 IPS
 
Image Segmentation (Q)
98% 728
11.8 IPS
 
Pose Estimation (SP)
0
 
Pose Estimation (HP)
0
 
Pose Estimation (Q)
98% 1870
2.19 IPS
 
Object Detection (SP)
100% 279
22.1 IPS
 
Object Detection (HP)
100% 280
22.2 IPS
 
Object Detection (Q)
87% 776
62.3 IPS
 
Face Detection (SP)
100% 665
7.90 IPS
 
Face Detection (HP)
100% 670
7.96 IPS
 
Face Detection (Q)
97% 1567
18.7 IPS
 
Depth Estimation (SP)
100% 617
4.75 IPS
 
Depth Estimation (HP)
99% 618
4.76 IPS
 
Depth Estimation (Q)
64% 1429
13.0 IPS
 
Style Transfer (SP)
100% 974
1.25 IPS
 
Style Transfer (HP)
100% 972
1.25 IPS
 
Style Transfer (Q)
98% 2293
2.96 IPS
 
Image Super-Resolution (SP)
100% 1286
47.5 IPS
 
Image Super-Resolution (HP)
100% 1392
51.4 IPS
 
Image Super-Resolution (Q)
97% 1100
40.8 IPS
 
Text Classification (SP)
100% 418
557.8 IPS
 
Text Classification (HP)
100% 418
558.2 IPS
 
Text Classification (Q)
91% 654
879.6 IPS
 
Machine Translation (SP)
100% 645
11.1 IPS
 
Machine Translation (HP)
100% 646
11.1 IPS
 
Machine Translation (Q)
57% 540
13.2 IPS
 

Compare

Set Baseline Geekbench 6 now available