Geekbench AI Score

935
Single Precision Score
1634
Half Precision Score
1767
Quantized Score
Geekbench AI 1.8.0 for Android AArch64

Result Information

Upload Date November 20 2026 08:13 AM
Views 2

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Samsung Exynos 990
System Information
Operating System Android 13
Model Samsung Galaxy Note20 Ultra
Model IDsamsung SM-N986B
Motherboard exynos990
Governorenergy_step
CPU Information
Name ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 83 architecture 8 variant 1 part 4 revision 0
Base Frequency 2.00 GHz
Cluster 14 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.50 GHz
Cluster 32 Cores @ 2.73 GHz
Memory Information
Size 10.64 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 448
83.4 IPS
 
Image Classification (HP)
100% 872
162.2 IPS
 
Image Classification (Q)
99% 1275
237.8 IPS
 
Image Segmentation (SP)
100% 528
8.56 IPS
 
Image Segmentation (HP)
100% 1103
17.9 IPS
 
Image Segmentation (Q)
98% 1388
22.6 IPS
 
Pose Estimation (SP)
100% 2088
2.44 IPS
 
Pose Estimation (HP)
92% 4351
5.11 IPS
 
Pose Estimation (Q)
96% 3512
4.11 IPS
 
Object Detection (SP)
100% 460
36.5 IPS
 
Object Detection (HP)
97% 894
71.2 IPS
 
Object Detection (Q)
85% 1238
99.7 IPS
 
Face Detection (SP)
100% 1358
16.1 IPS
 
Face Detection (HP)
100% 2495
29.6 IPS
 
Face Detection (Q)
97% 2965
35.4 IPS
 
Depth Estimation (SP)
100% 1722
13.3 IPS
 
Depth Estimation (HP)
98% 3108
24.0 IPS
 
Depth Estimation (Q)
64% 3123
28.8 IPS
 
Style Transfer (SP)
89% 3663
4.76 IPS
 
Style Transfer (HP)
88% 4870
6.32 IPS
 
Style Transfer (Q)
98% 7668
9.89 IPS
 
Image Super-Resolution (SP)
100% 955
35.3 IPS
 
Image Super-Resolution (HP)
92% 1788
66.5 IPS
 
Image Super-Resolution (Q)
97% 1904
70.6 IPS
 
Text Classification (SP)
100% 412
550.4 IPS
 
Text Classification (HP)
100% 651
869.0 IPS
 
Text Classification (Q)
93% 638
857.1 IPS
 
Machine Translation (SP)
100% 674
11.6 IPS
 
Machine Translation (HP)
96% 830
14.4 IPS
 
Machine Translation (Q)
55% 448
12.0 IPS
 

Compare

Set Baseline Geekbench AI now available