Geekbench AI Score

918
Single Precision Score
1590
Half Precision Score
1728
Quantized Score
Geekbench AI 1.8.0 for Android AArch64

Result Information

Upload Date November 20 2026 08:18 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% 465
86.4 IPS
 
Image Classification (HP)
100% 847
157.5 IPS
 
Image Classification (Q)
99% 1254
234.0 IPS
 
Image Segmentation (SP)
100% 554
8.99 IPS
 
Image Segmentation (HP)
100% 1088
17.6 IPS
 
Image Segmentation (Q)
98% 1380
22.4 IPS
 
Pose Estimation (SP)
100% 2034
2.37 IPS
 
Pose Estimation (HP)
92% 4090
4.80 IPS
 
Pose Estimation (Q)
96% 3278
3.84 IPS
 
Object Detection (SP)
100% 422
33.5 IPS
 
Object Detection (HP)
97% 869
69.2 IPS
 
Object Detection (Q)
85% 1226
98.8 IPS
 
Face Detection (SP)
100% 1306
15.5 IPS
 
Face Detection (HP)
100% 2473
29.4 IPS
 
Face Detection (Q)
97% 2913
34.7 IPS
 
Depth Estimation (SP)
100% 1682
13.0 IPS
 
Depth Estimation (HP)
98% 3032
23.4 IPS
 
Depth Estimation (Q)
64% 3041
28.1 IPS
 
Style Transfer (SP)
89% 3505
4.55 IPS
 
Style Transfer (HP)
88% 4580
5.95 IPS
 
Style Transfer (Q)
98% 7533
9.71 IPS
 
Image Super-Resolution (SP)
100% 938
34.6 IPS
 
Image Super-Resolution (HP)
92% 1731
64.3 IPS
 
Image Super-Resolution (Q)
97% 1888
70.0 IPS
 
Text Classification (SP)
100% 412
549.8 IPS
 
Text Classification (HP)
100% 648
865.2 IPS
 
Text Classification (Q)
93% 613
823.7 IPS
 
Machine Translation (SP)
100% 651
11.2 IPS
 
Machine Translation (HP)
96% 822
14.2 IPS
 
Machine Translation (Q)
55% 442
11.9 IPS
 

Compare

Set Baseline Geekbench AI now available