Geekbench AI Score

389
Single Precision Score
12093
Half Precision Score
28244
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date December 28 2024 12:41 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm Snapdragon 8 Gen 2
System Information
Operating System Android 14
Model Samsung Galaxy S23
Model IDsamsung SM-S911B
Motherboard kalama
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3406 revision 0
Base Frequency 2.02 GHz
Cluster 13 Cores @ 2.02 GHz
Cluster 24 Cores @ 2.80 GHz
Cluster 31 Core @ 3.36 GHz
Memory Information
Size 6.89 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 297
55.2 IPS
 
Image Classification (HP)
100% 13198
2.45 KIPS
 
Image Classification (Q)
97% 32755
6.11 KIPS
 
Image Segmentation (SP)
100% 377
6.12 IPS
 
Image Segmentation (HP)
100% 7859
127.4 IPS
 
Image Segmentation (Q)
98% 20398
331.7 IPS
 
Pose Estimation (SP)
100% 523
0.61 IPS
 
Pose Estimation (HP)
100% 73756
86.1 IPS
 
Pose Estimation (Q)
98% 294256
344.4 IPS
 
Object Detection (SP)
100% 231
18.3 IPS
 
Object Detection (HP)
100% 12103
960.0 IPS
 
Object Detection (Q)
86% 13024
1.05 KIPS
 
Face Detection (SP)
100% 521
6.19 IPS
 
Face Detection (HP)
100% 25353
301.2 IPS
 
Face Detection (Q)
97% 84909
1.01 KIPS
 
Depth Estimation (SP)
100% 505
3.89 IPS
 
Depth Estimation (HP)
99% 43306
333.6 IPS
 
Depth Estimation (Q)
63% 82014
768.0 IPS
 
Style Transfer (SP)
100% 823
1.06 IPS
 
Style Transfer (HP)
24% 2962
89.6 IPS
 
Style Transfer (Q)
98% 220766
284.7 IPS
 
Image Super-Resolution (SP)
100% 219
8.08 IPS
 
Image Super-Resolution (HP)
100% 31687
1.17 KIPS
 
Image Super-Resolution (Q)
97% 79028
2.93 KIPS
 
Text Classification (SP)
100% 273
364.6 IPS
 
Text Classification (HP)
100% 2453
3.27 KIPS
 
Text Classification (Q)
93% 5353
7.18 KIPS
 
Machine Translation (SP)
100% 458
7.88 IPS
 
Machine Translation (HP)
100% 2860
49.3 IPS
 
Machine Translation (Q)
30% 194
39.0 IPS
 

Compare

Set Baseline Geekbench 6 now available