Geekbench AI Score

289
Single Precision Score
288
Half Precision Score
717
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User Namelessmint
Upload Date January 17 2025 12:00 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend NNAPI
Device ARM ARMv8
System Information
Operating System Android 14
Model samsung SM-S711B
Model IDsamsung SM-S711B
Motherboard s5e9925
Governorenergy_aware
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 1.82 GHz
Cluster 14 Cores @ 1.82 GHz
Cluster 23 Cores @ 2.52 GHz
Cluster 31 Core @ 2.80 GHz
Memory Information
Size 7.12 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 175
32.6 IPS
 
Image Classification (HP)
100% 175
32.6 IPS
 
Image Classification (Q)
99% 507
94.6 IPS
 
Image Segmentation (SP)
100% 225
3.64 IPS
 
Image Segmentation (HP)
100% 226
3.66 IPS
 
Image Segmentation (Q)
98% 536
8.72 IPS
 
Pose Estimation (SP)
100% 300
0.35 IPS
 
Pose Estimation (HP)
100% 292
0.34 IPS
 
Pose Estimation (Q)
98% 1238
1.45 IPS
 
Object Detection (SP)
100% 170
13.5 IPS
 
Object Detection (HP)
100% 171
13.6 IPS
 
Object Detection (Q)
87% 529
42.4 IPS
 
Face Detection (SP)
100% 452
5.37 IPS
 
Face Detection (HP)
100% 454
5.39 IPS
 
Face Detection (Q)
97% 1118
13.3 IPS
 
Depth Estimation (SP)
100% 372
2.87 IPS
 
Depth Estimation (HP)
99% 370
2.85 IPS
 
Depth Estimation (Q)
64% 902
8.19 IPS
 
Style Transfer (SP)
100% 653
0.84 IPS
 
Style Transfer (HP)
100% 652
0.84 IPS
 
Style Transfer (Q)
98% 1663
2.14 IPS
 
Image Super-Resolution (SP)
100% 191
7.06 IPS
 
Image Super-Resolution (HP)
100% 191
7.05 IPS
 
Image Super-Resolution (Q)
97% 719
26.6 IPS
 
Text Classification (SP)
100% 238
317.3 IPS
 
Text Classification (HP)
100% 238
317.6 IPS
 
Text Classification (Q)
91% 459
616.4 IPS
 
Machine Translation (SP)
100% 411
7.08 IPS
 
Machine Translation (HP)
100% 408
7.03 IPS
 
Machine Translation (Q)
57% 369
9.01 IPS
 

Compare

Set Baseline Geekbench 6 now available