Geekbench AI Score

921
Single Precision Score
1401
Half Precision Score
1410
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date June 13 2025 10:49 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend GPU
Device Qualcomm Snapdragon 8 Gen 3
System Information
Operating System Android 15
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% 579
107.7 IPS
 
Image Classification (HP)
100% 512
95.3 IPS
 
Image Classification (Q)
96% 495
92.5 IPS
 
Image Segmentation (SP)
100% 1205
19.5 IPS
 
Image Segmentation (HP)
100% 2398
38.9 IPS
 
Image Segmentation (Q)
98% 2297
37.3 IPS
 
Pose Estimation (SP)
100% 1029
1.20 IPS
 
Pose Estimation (HP)
100% 1790
2.09 IPS
 
Pose Estimation (Q)
96% 1781
2.09 IPS
 
Object Detection (SP)
100% 550
43.6 IPS
 
Object Detection (HP)
100% 775
61.5 IPS
 
Object Detection (Q)
87% 754
60.6 IPS
 
Face Detection (SP)
100% 2035
24.2 IPS
 
Face Detection (HP)
100% 3414
40.6 IPS
 
Face Detection (Q)
97% 3378
40.3 IPS
 
Depth Estimation (SP)
100% 1317
10.1 IPS
 
Depth Estimation (HP)
99% 2654
20.5 IPS
 
Depth Estimation (Q)
63% 2203
20.4 IPS
 
Style Transfer (SP)
100% 4561
5.86 IPS
 
Style Transfer (HP)
100% 7576
9.74 IPS
 
Style Transfer (Q)
98% 7630
9.84 IPS
 
Image Super-Resolution (SP)
100% 402
14.8 IPS
 
Image Super-Resolution (HP)
100% 1062
39.2 IPS
 
Image Super-Resolution (Q)
97% 1055
39.1 IPS
 
Text Classification (SP)
100% 383
510.9 IPS
 
Text Classification (HP)
100% 395
526.9 IPS
 
Text Classification (Q)
91% 666
895.7 IPS
 
Machine Translation (SP)
100% 594
10.2 IPS
 
Machine Translation (HP)
100% 596
10.3 IPS
 
Machine Translation (Q)
57% 511
12.5 IPS
 

Compare

Set Baseline Geekbench 6 now available