Geekbench AI Score

304
Single Precision Score
301
Half Precision Score
13426
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

User n0idea
Upload Date November 13 2024 12:24 AM
Views 6

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm Snapdragon 888
System Information
Operating System Android 14
Model Samsung Galaxy S21 Ultra 5G
Model IDsamsung SM-G998U1
Motherboard lahaina
Governorschedutil
CPU Information
Name ARM SM8350
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3396 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 10.07 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 177
32.8 IPS
 
Image Classification (HP)
100% 174
32.3 IPS
 
Image Classification (Q)
99% 11314
2.11 KIPS
 
Image Segmentation (SP)
100% 236
3.83 IPS
 
Image Segmentation (HP)
100% 227
3.67 IPS
 
Image Segmentation (Q)
98% 11978
194.8 IPS
 
Pose Estimation (SP)
100% 305
0.36 IPS
 
Pose Estimation (HP)
100% 305
0.36 IPS
 
Pose Estimation (Q)
94% 99586
116.8 IPS
 
Object Detection (SP)
100% 179
14.2 IPS
 
Object Detection (HP)
100% 172
13.7 IPS
 
Object Detection (Q)
88% 6526
522.8 IPS
 
Face Detection (SP)
100% 461
5.48 IPS
 
Face Detection (HP)
100% 469
5.57 IPS
 
Face Detection (Q)
97% 34601
412.6 IPS
 
Depth Estimation (SP)
100% 374
2.88 IPS
 
Depth Estimation (HP)
99% 391
3.01 IPS
 
Depth Estimation (Q)
64% 35932
330.8 IPS
 
Style Transfer (SP)
100% 612
0.79 IPS
 
Style Transfer (HP)
100% 639
0.82 IPS
 
Style Transfer (Q)
98% 100861
130.1 IPS
 
Image Super-Resolution (SP)
100% 200
7.40 IPS
 
Image Super-Resolution (HP)
100% 192
7.09 IPS
 
Image Super-Resolution (Q)
97% 31702
1.17 KIPS
 
Text Classification (SP)
100% 312
416.2 IPS
 
Text Classification (HP)
100% 307
409.2 IPS
 
Text Classification (Q)
94% 2665
3.58 KIPS
 
Machine Translation (SP)
100% 453
7.80 IPS
 
Machine Translation (HP)
100% 433
7.46 IPS
 
Machine Translation (Q)
37% 204
20.6 IPS
 

Compare

Set Baseline Geekbench 6 now available