Geekbench AI Score

1930
Single Precision Score
2143
Half Precision Score
3197
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date June 19 2025 12:29 PM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 13
Model Google rauru
Model IDGoogle rauru
Motherboard navi
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3461 revision 1
Base Frequency 2.40 GHz
Cluster 14 Cores @ 2.40 GHz
Cluster 23 Cores @ 3.30 GHz
Cluster 31 Core @ 3.63 GHz
Memory Information
Size 14.14 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1848
343.7 IPS
 
Image Classification (HP)
100% 1918
356.6 IPS
 
Image Classification (Q)
100% 2808
522.2 IPS
 
Image Segmentation (SP)
100% 2209
35.8 IPS
 
Image Segmentation (HP)
100% 2209
35.8 IPS
 
Image Segmentation (Q)
98% 3149
51.2 IPS
 
Pose Estimation (SP)
100% 3671
4.28 IPS
 
Pose Estimation (HP)
100% 3589
4.19 IPS
 
Pose Estimation (Q)
84% 7240
8.59 IPS
 
Object Detection (SP)
98% 426
33.9 IPS
 
Object Detection (HP)
98% 1827
145.4 IPS
 
Object Detection (Q)
83% 2528
204.2 IPS
 
Face Detection (SP)
100% 3439
40.9 IPS
 
Face Detection (HP)
100% 3487
41.4 IPS
 
Face Detection (Q)
95% 6066
72.4 IPS
 
Depth Estimation (SP)
99% 3915
30.3 IPS
 
Depth Estimation (HP)
99% 3919
30.3 IPS
 
Depth Estimation (Q)
64% 6074
55.6 IPS
 
Style Transfer (SP)
89% 8399
10.9 IPS
 
Style Transfer (HP)
89% 8919
11.6 IPS
 
Style Transfer (Q)
98% 16432
21.2 IPS
 
Image Super-Resolution (SP)
100% 534
19.7 IPS
 
Image Super-Resolution (HP)
100% 1429
52.8 IPS
 
Image Super-Resolution (Q)
97% 868
32.2 IPS
 
Text Classification (SP)
100% 901
1.20 KIPS
 
Text Classification (HP)
99% 214
285.1 IPS
 
Text Classification (Q)
88% 1367
1.84 KIPS
 
Machine Translation (SP)
100% 2069
35.6 IPS
 
Machine Translation (HP)
100% 1974
34.0 IPS
 
Machine Translation (Q)
50% 960
34.1 IPS
 

Compare

Set Baseline Geekbench 6 now available