Google Pixel 8a
Geekbench AI Score
368
Single Precision Score
4090
Half Precision Score
7390
Quantized Score
Geekbench AI 1.6.1 for Android AArch64
Result Information
| User | M91 |
| Upload Date | January 10 2026 11:47 AM |
| Views | 12 |
System Information
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | Google Tensor G3 |
| System Information | |
|---|---|
| Operating System | Android 16 |
| Model | Google Pixel 8a |
| Model ID | Google Pixel 8a |
| Motherboard | akita |
| Governor | sched_pixel |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 9 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3406 revision 0 |
| Base Frequency | 1.70 GHz |
| Cluster 1 | 4 Cores @ 1.70 GHz |
| Cluster 2 | 4 Cores @ 2.37 GHz |
| Cluster 3 | 1 Core @ 2.91 GHz |
| Memory Information | |
|---|---|
| Size | 7.40 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
239
44.4 IPS |
|
|
Image Classification (HP)
|
100% |
5606
1.04 KIPS |
|
|
Image Classification (Q)
|
99% |
7629
1.42 KIPS |
|
|
Image Segmentation (SP)
|
100% |
297
4.82 IPS |
|
|
Image Segmentation (HP)
|
100% |
7524
122.0 IPS |
|
|
Image Segmentation (Q)
|
98% |
15924
258.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
368
0.43 IPS |
|
|
Pose Estimation (HP)
|
100% |
30613
35.7 IPS |
|
|
Pose Estimation (Q)
|
97% |
61836
72.4 IPS |
|
|
Object Detection (SP)
|
100% |
217
17.2 IPS |
|
|
Object Detection (HP)
|
100% |
4458
353.6 IPS |
|
|
Object Detection (Q)
|
87% |
5238
420.2 IPS |
|
|
Face Detection (SP)
|
100% |
547
6.50 IPS |
|
|
Face Detection (HP)
|
100% |
11807
140.3 IPS |
|
|
Face Detection (Q)
|
97% |
32592
388.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
487
3.75 IPS |
|
|
Depth Estimation (HP)
|
99% |
29185
224.9 IPS |
|
|
Depth Estimation (Q)
|
64% |
33758
310.8 IPS |
|
|
Style Transfer (SP)
|
100% |
694
0.89 IPS |
|
|
Style Transfer (HP)
|
100% |
592
0.76 IPS |
|
|
Style Transfer (Q)
|
98% |
1566
2.02 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
264
9.76 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
7579
279.9 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
13586
503.4 IPS |
|
|
Text Classification (SP)
|
100% |
322
429.2 IPS |
|
|
Text Classification (HP)
|
100% |
321
428.9 IPS |
|
|
Text Classification (Q)
|
92% |
1649
2.22 KIPS |
|
|
Machine Translation (SP)
|
100% |
518
8.91 IPS |
|
|
Machine Translation (HP)
|
100% |
459
7.91 IPS |
|
|
Machine Translation (Q)
|
57% |
320
7.81 IPS |
