Geekbench AI Score

360
Single Precision Score
15738
Half Precision Score
37971
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date September 16 2024 11:04 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend QNN
Device ARM ARMv8
System Information
Operating System Android 14
Model samsung SM-F956Q
Model IDsamsung SM-F956Q
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 10.86 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 306
56.9 IPS
 
Image Classification (HP)
100% 17378
3.23 KIPS
 
Image Classification (Q)
97% 43196
8.06 KIPS
 
Image Segmentation (SP)
100% 371
6.02 IPS
 
Image Segmentation (HP)
100% 11041
179.0 IPS
 
Image Segmentation (Q)
98% 29328
476.9 IPS
 
Pose Estimation (SP)
100% 401
0.47 IPS
 
Pose Estimation (HP)
100% 99488
116.1 IPS
 
Pose Estimation (Q)
98% 394326
461.5 IPS
 
Object Detection (SP)
100% 190
15.1 IPS
 
Object Detection (HP)
100% 15127
1.20 KIPS
 
Object Detection (Q)
86% 18088
1.45 KIPS
 
Face Detection (SP)
100% 488
5.80 IPS
 
Face Detection (HP)
100% 32347
384.4 IPS
 
Face Detection (Q)
97% 108329
1.29 KIPS
 
Depth Estimation (SP)
100% 414
3.19 IPS
 
Depth Estimation (HP)
99% 58034
447.1 IPS
 
Depth Estimation (Q)
63% 112151
1.05 KIPS
 
Style Transfer (SP)
100% 677
0.87 IPS
 
Style Transfer (HP)
24% 3839
116.1 IPS
 
Style Transfer (Q)
98% 303256
391.1 IPS
 
Image Super-Resolution (SP)
100% 219
8.10 IPS
 
Image Super-Resolution (HP)
100% 44155
1.63 KIPS
 
Image Super-Resolution (Q)
97% 105274
3.90 KIPS
 
Text Classification (SP)
100% 288
383.8 IPS
 
Text Classification (HP)
100% 3082
4.11 KIPS
 
Text Classification (Q)
93% 6709
9.00 KIPS
 
Machine Translation (SP)
100% 493
8.49 IPS
 
Machine Translation (HP)
100% 3293
56.7 IPS
 
Machine Translation (Q)
30% 265
53.3 IPS
 

Compare

Set Baseline Geekbench 6 now available