Geekbench AI Score

2858
Single Precision Score
2920
Half Precision Score
4612
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

User Masatako123
Upload Date December 23 2024 11:55 AM
Views 9

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 14
Model samsung SM-S921Q
Model IDsamsung SM-S921Q
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 6.95 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2052
381.7 IPS
 
Image Classification (HP)
100% 2499
464.8 IPS
 
Image Classification (Q)
100% 3389
630.2 IPS
 
Image Segmentation (SP)
100% 2639
42.8 IPS
 
Image Segmentation (HP)
100% 2739
44.4 IPS
 
Image Segmentation (Q)
98% 4130
67.2 IPS
 
Pose Estimation (SP)
100% 4386
5.12 IPS
 
Pose Estimation (HP)
100% 4261
4.97 IPS
 
Pose Estimation (Q)
84% 9856
11.7 IPS
 
Object Detection (SP)
98% 2002
159.3 IPS
 
Object Detection (HP)
98% 2179
173.4 IPS
 
Object Detection (Q)
83% 3530
285.2 IPS
 
Face Detection (SP)
100% 4096
48.7 IPS
 
Face Detection (HP)
100% 4242
50.4 IPS
 
Face Detection (Q)
95% 7774
92.8 IPS
 
Depth Estimation (SP)
99% 4228
32.7 IPS
 
Depth Estimation (HP)
99% 4143
32.0 IPS
 
Depth Estimation (Q)
64% 7526
68.9 IPS
 
Style Transfer (SP)
89% 10178
13.2 IPS
 
Style Transfer (HP)
89% 10138
13.2 IPS
 
Style Transfer (Q)
98% 20692
26.7 IPS
 
Image Super-Resolution (SP)
100% 2205
81.4 IPS
 
Image Super-Resolution (HP)
100% 2288
84.5 IPS
 
Image Super-Resolution (Q)
97% 5227
193.7 IPS
 
Text Classification (SP)
100% 1080
1.44 KIPS
 
Text Classification (HP)
99% 982
1.31 KIPS
 
Text Classification (Q)
88% 1512
2.04 KIPS
 
Machine Translation (SP)
100% 1823
31.4 IPS
 
Machine Translation (HP)
100% 1773
30.5 IPS
 
Machine Translation (Q)
50% 935
33.2 IPS
 

Compare

Set Baseline Geekbench 6 now available