Geekbench AI Score

1179
Single Precision Score
1674
Half Precision Score
1531
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date December 01 2024 10:45 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device Qualcomm Snapdragon 8 Gen 3
System Information
Operating System Android 14
Model Samsung Galaxy S24 Ultra
Model IDsamsung SM-S928B
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 10.83 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 969
180.3 IPS
 
Image Classification (HP)
100% 639
118.9 IPS
 
Image Classification (Q)
96% 637
118.9 IPS
 
Image Segmentation (SP)
100% 1175
19.0 IPS
 
Image Segmentation (HP)
100% 1453
23.6 IPS
 
Image Segmentation (Q)
98% 1020
16.6 IPS
 
Pose Estimation (SP)
100% 1120
1.31 IPS
 
Pose Estimation (HP)
100% 2734
3.19 IPS
 
Pose Estimation (Q)
96% 2731
3.20 IPS
 
Object Detection (SP)
100% 683
54.2 IPS
 
Object Detection (HP)
100% 1031
81.8 IPS
 
Object Detection (Q)
87% 726
58.3 IPS
 
Face Detection (SP)
100% 2520
29.9 IPS
 
Face Detection (HP)
100% 3087
36.7 IPS
 
Face Detection (Q)
97% 2401
28.6 IPS
 
Depth Estimation (SP)
100% 1849
14.2 IPS
 
Depth Estimation (HP)
99% 3902
30.1 IPS
 
Depth Estimation (Q)
63% 3256
30.2 IPS
 
Style Transfer (SP)
100% 7199
9.25 IPS
 
Style Transfer (HP)
100% 11704
15.0 IPS
 
Style Transfer (Q)
98% 11651
15.0 IPS
 
Image Super-Resolution (SP)
100% 543
20.1 IPS
 
Image Super-Resolution (HP)
100% 1429
52.8 IPS
 
Image Super-Resolution (Q)
97% 1349
50.0 IPS
 
Text Classification (SP)
100% 464
618.8 IPS
 
Text Classification (HP)
100% 466
622.4 IPS
 
Text Classification (Q)
91% 746
1.00 KIPS
 
Machine Translation (SP)
100% 708
12.2 IPS
 
Machine Translation (HP)
100% 704
12.1 IPS
 
Machine Translation (Q)
57% 602
14.7 IPS
 

Compare

Set Baseline Geekbench 6 now available