Geekbench AI Score

1367
Single Precision Score
1460
Half Precision Score
2135
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date June 14 2025 11:00 AM
Views 3

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 16
Model Google Pixel 9a
Model IDGoogle Pixel 9a
Motherboard tegu
Governorsched_pixel
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3458 revision 1
Base Frequency 1.95 GHz
Cluster 14 Cores @ 1.95 GHz
Cluster 23 Cores @ 2.60 GHz
Cluster 31 Core @ 3.10 GHz
Memory Information
Size 7.14 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1333
247.9 IPS
 
Image Classification (HP)
100% 1473
274.0 IPS
 
Image Classification (Q)
100% 2379
442.4 IPS
 
Image Segmentation (SP)
100% 1436
23.3 IPS
 
Image Segmentation (HP)
100% 1550
25.1 IPS
 
Image Segmentation (Q)
98% 2437
39.6 IPS
 
Pose Estimation (SP)
100% 2550
2.98 IPS
 
Pose Estimation (HP)
100% 2226
2.60 IPS
 
Pose Estimation (Q)
84% 4638
5.50 IPS
 
Object Detection (SP)
98% 817
65.0 IPS
 
Object Detection (HP)
98% 1025
81.6 IPS
 
Object Detection (Q)
83% 856
69.2 IPS
 
Face Detection (SP)
100% 1218
14.5 IPS
 
Face Detection (HP)
100% 1972
23.4 IPS
 
Face Detection (Q)
95% 2749
32.8 IPS
 
Depth Estimation (SP)
99% 2130
16.5 IPS
 
Depth Estimation (HP)
99% 2136
16.5 IPS
 
Depth Estimation (Q)
64% 3395
31.1 IPS
 
Style Transfer (SP)
89% 5108
6.63 IPS
 
Style Transfer (HP)
89% 5150
6.69 IPS
 
Style Transfer (Q)
98% 9761
12.6 IPS
 
Image Super-Resolution (SP)
100% 947
35.0 IPS
 
Image Super-Resolution (HP)
100% 919
33.9 IPS
 
Image Super-Resolution (Q)
97% 2491
92.3 IPS
 
Text Classification (SP)
100% 471
629.0 IPS
 
Text Classification (HP)
99% 464
619.5 IPS
 
Text Classification (Q)
88% 820
1.11 KIPS
 
Machine Translation (SP)
100% 970
16.7 IPS
 
Machine Translation (HP)
100% 919
15.8 IPS
 
Machine Translation (Q)
50% 461
16.4 IPS
 

Compare

Set Baseline Geekbench 6 now available