Geekbench AI Score

308
Single Precision Score
333
Half Precision Score
1060
Quantized Score
Geekbench AI 1.8.0 for Android AArch64

Result Information

User saiht
Upload Date September 28 2026 07:31 AM
Views 15

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device Samsung Exynos 2400
System Information
Operating System Android 16
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 7.05 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 293
54.4 IPS
 
Image Classification (HP)
100% 288
53.5 IPS
 
Image Classification (Q)
99% 752
140.2 IPS
 
Image Segmentation (SP)
100% 781
12.7 IPS
 
Image Segmentation (HP)
100% 1456
23.6 IPS
 
Image Segmentation (Q)
98% 775
12.6 IPS
 
Pose Estimation (SP)
0
 
Pose Estimation (HP)
0
 
Pose Estimation (Q)
98% 1940
2.27 IPS
 
Object Detection (SP)
100% 273
21.7 IPS
 
Object Detection (HP)
100% 272
21.6 IPS
 
Object Detection (Q)
87% 791
63.5 IPS
 
Face Detection (SP)
100% 648
7.70 IPS
 
Face Detection (HP)
100% 653
7.76 IPS
 
Face Detection (Q)
97% 1597
19.0 IPS
 
Depth Estimation (SP)
100% 561
4.32 IPS
 
Depth Estimation (HP)
99% 565
4.35 IPS
 
Depth Estimation (Q)
64% 1406
12.8 IPS
 
Style Transfer (SP)
100% 919
1.18 IPS
 
Style Transfer (HP)
100% 922
1.19 IPS
 
Style Transfer (Q)
98% 2250
2.90 IPS
 
Image Super-Resolution (SP)
100% 1453
53.7 IPS
 
Image Super-Resolution (HP)
100% 1678
62.0 IPS
 
Image Super-Resolution (Q)
97% 1077
39.9 IPS
 
Text Classification (SP)
100% 414
552.8 IPS
 
Text Classification (HP)
100% 422
563.1 IPS
 
Text Classification (Q)
91% 687
923.8 IPS
 
Machine Translation (SP)
100% 630
10.9 IPS
 
Machine Translation (HP)
100% 625
10.8 IPS
 
Machine Translation (Q)
57% 536
13.1 IPS
 

Compare

Set Baseline Geekbench AI now available