Geekbench AI Score

2489
Single Precision Score
2603
Half Precision Score
3689
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

User Placo
Upload Date October 09 2024 08:42 PM
Views 9

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model samsung SM-F956B
Model IDsamsung SM-F956B
Motherboard pineapple
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3458 revision 1
Base Frequency 2.26 GHz
Cluster 12 Cores @ 2.27 GHz
Cluster 22 Cores @ 2.96 GHz
Cluster 33 Cores @ 3.15 GHz
Cluster 41 Core @ 3.40 GHz
Memory Information
Size 10.86 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2030
377.4 IPS
 
Image Classification (HP)
100% 2218
412.5 IPS
 
Image Classification (Q)
100% 2645
492.0 IPS
 
Image Segmentation (SP)
100% 2622
42.5 IPS
 
Image Segmentation (HP)
100% 2644
42.9 IPS
 
Image Segmentation (Q)
98% 4358
70.9 IPS
 
Pose Estimation (SP)
100% 3995
4.66 IPS
 
Pose Estimation (HP)
100% 3926
4.58 IPS
 
Pose Estimation (Q)
84% 8989
10.7 IPS
 
Object Detection (SP)
98% 2071
164.8 IPS
 
Object Detection (HP)
98% 2146
170.8 IPS
 
Object Detection (Q)
83% 3107
251.0 IPS
 
Face Detection (SP)
100% 4194
49.8 IPS
 
Face Detection (HP)
100% 4167
49.5 IPS
 
Face Detection (Q)
95% 6674
79.7 IPS
 
Depth Estimation (SP)
99% 4299
33.2 IPS
 
Depth Estimation (HP)
99% 4273
33.0 IPS
 
Depth Estimation (Q)
64% 5372
49.2 IPS
 
Style Transfer (SP)
89% 8283
10.8 IPS
 
Style Transfer (HP)
89% 8330
10.8 IPS
 
Style Transfer (Q)
98% 15520
20.0 IPS
 
Image Super-Resolution (SP)
100% 1644
60.7 IPS
 
Image Super-Resolution (HP)
100% 1718
63.4 IPS
 
Image Super-Resolution (Q)
97% 3721
137.9 IPS
 
Text Classification (SP)
100% 677
903.3 IPS
 
Text Classification (HP)
99% 727
970.0 IPS
 
Text Classification (Q)
88% 957
1.29 KIPS
 
Machine Translation (SP)
100% 1249
21.5 IPS
 
Machine Translation (HP)
100% 1562
26.9 IPS
 
Machine Translation (Q)
50% 732
26.0 IPS
 

Compare

Set Baseline Geekbench 6 now available