Geekbench AI Score

566
Single Precision Score
27214
Half Precision Score
60134
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date February 17 2025 04:33 PM
Views 14

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device Qualcomm ARMv8
System Information
Operating System Android 15
Model samsung SM-S931B
Model IDsamsung SM-S931B
Motherboard sun
Governorwalt
CPU Information
Name Qualcomm ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 3 part 1 revision 4
Base Frequency 3.53 GHz
Cluster 16 Cores @ 3.53 GHz
Cluster 22 Cores @ 4.47 GHz
Memory Information
Size 10.86 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 459
85.4 IPS
 
Image Classification (HP)
100% 21657
4.03 KIPS
 
Image Classification (Q)
97% 49475
9.23 KIPS
 
Image Segmentation (SP)
100% 577
9.36 IPS
 
Image Segmentation (HP)
100% 13677
221.7 IPS
 
Image Segmentation (Q)
98% 39176
637.0 IPS
 
Pose Estimation (SP)
100% 592
0.69 IPS
 
Pose Estimation (HP)
100% 123315
143.9 IPS
 
Pose Estimation (Q)
98% 478321
559.8 IPS
 
Object Detection (SP)
100% 307
24.3 IPS
 
Object Detection (HP)
100% 19372
1.54 KIPS
 
Object Detection (Q)
85% 22378
1.80 KIPS
 
Face Detection (SP)
100% 942
11.2 IPS
 
Face Detection (HP)
100% 41198
489.5 IPS
 
Face Detection (Q)
97% 141688
1.69 KIPS
 
Depth Estimation (SP)
100% 646
4.98 IPS
 
Depth Estimation (HP)
99% 83298
641.8 IPS
 
Depth Estimation (Q)
63% 135432
1.25 KIPS
 
Style Transfer (SP)
100% 1169
1.50 IPS
 
Style Transfer (HP)
98% 98601
127.1 IPS
 
Style Transfer (Q)
98% 490076
632.0 IPS
 
Image Super-Resolution (SP)
100% 366
13.5 IPS
 
Image Super-Resolution (HP)
100% 53179
1.96 KIPS
 
Image Super-Resolution (Q)
97% 134270
4.98 KIPS
 
Text Classification (SP)
100% 394
526.5 IPS
 
Text Classification (HP)
100% 3877
5.17 KIPS
 
Text Classification (Q)
93% 7903
10.6 KIPS
 
Machine Translation (SP)
100% 687
11.8 IPS
 
Machine Translation (HP)
100% 4514
77.8 IPS
 
Machine Translation (Q)
56% 2987
77.0 IPS
 

Compare

Set Baseline Geekbench 6 now available