Geekbench AI Score

388
Single Precision Score
652
Half Precision Score
725
Quantized Score
Geekbench AI 1.7.0 for Android AArch64

Result Information

User Mmbashaikh
Upload Date April 17 2026 07:30 PM
Views 19

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device Qualcomm Snapdragon 7s Gen 2
System Information
Operating System Android 15
Model Xiaomi Redmi Note 13 Pro
Model IDXiaomi 2312DRA50G
Motherboard garnet
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 2
Base Frequency 1.96 GHz
Cluster 14 Cores @ 1.96 GHz
Cluster 24 Cores @ 2.40 GHz
Memory Information
Size 11.01 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 275
51.1 IPS
 
Image Classification (HP)
100% 553
102.9 IPS
 
Image Classification (Q)
99% 819
152.7 IPS
 
Image Segmentation (SP)
100% 376
6.10 IPS
 
Image Segmentation (HP)
100% 586
9.50 IPS
 
Image Segmentation (Q)
98% 909
14.8 IPS
 
Pose Estimation (SP)
100% 1343
1.57 IPS
 
Pose Estimation (HP)
92% 2656
3.12 IPS
 
Pose Estimation (Q)
96% 1731
2.03 IPS
 
Object Detection (SP)
100% 248
19.7 IPS
 
Object Detection (HP)
97% 290
23.1 IPS
 
Object Detection (Q)
85% 396
31.9 IPS
 
Face Detection (SP)
100% 342
4.06 IPS
 
Face Detection (HP)
100% 659
7.83 IPS
 
Face Detection (Q)
97% 798
9.52 IPS
 
Depth Estimation (SP)
100% 509
3.92 IPS
 
Depth Estimation (HP)
98% 1027
7.94 IPS
 
Depth Estimation (Q)
64% 1006
9.29 IPS
 
Style Transfer (SP)
89% 1157
1.50 IPS
 
Style Transfer (HP)
88% 1586
2.06 IPS
 
Style Transfer (Q)
98% 2534
3.27 IPS
 
Image Super-Resolution (SP)
100% 278
10.3 IPS
 
Image Super-Resolution (HP)
92% 573
21.3 IPS
 
Image Super-Resolution (Q)
97% 634
23.5 IPS
 
Text Classification (SP)
100% 154
205.5 IPS
 
Text Classification (HP)
100% 245
326.5 IPS
 
Text Classification (Q)
93% 261
350.1 IPS
 
Machine Translation (SP)
100% 267
4.61 IPS
 
Machine Translation (HP)
96% 372
6.44 IPS
 
Machine Translation (Q)
55% 236
6.35 IPS
 

Compare

Set Baseline Geekbench 6 now available