Geekbench AI Score

916
Single Precision Score
919
Half Precision Score
2069
Quantized Score
Geekbench AI 1.5.0 for Android AArch64

Result Information

Upload Date November 08 2025 02:30 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device MediaTek Dimensity 7300
System Information
Operating System Android 15
Model Nothing CMF Phone 1
Model IDNothing A015
Motherboard Tetris
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 0
Base Frequency 2.00 GHz
Cluster 14 Cores @ 2.00 GHz
Cluster 24 Cores @ 2.50 GHz
Memory Information
Size 7.25 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 465
86.5 IPS
 
Image Classification (HP)
100% 466
86.7 IPS
 
Image Classification (Q)
100% 1480
275.3 IPS
 
Image Segmentation (SP)
100% 548
8.88 IPS
 
Image Segmentation (HP)
100% 546
8.85 IPS
 
Image Segmentation (Q)
98% 1726
28.1 IPS
 
Pose Estimation (SP)
100% 1933
2.26 IPS
 
Pose Estimation (HP)
100% 2011
2.35 IPS
 
Pose Estimation (Q)
84% 3853
4.57 IPS
 
Object Detection (SP)
100% 460
36.5 IPS
 
Object Detection (HP)
100% 462
36.6 IPS
 
Object Detection (Q)
83% 1412
114.0 IPS
 
Face Detection (SP)
100% 1075
12.8 IPS
 
Face Detection (HP)
100% 1069
12.7 IPS
 
Face Detection (Q)
95% 3493
41.7 IPS
 
Depth Estimation (SP)
100% 1484
11.4 IPS
 
Depth Estimation (HP)
99% 1514
11.7 IPS
 
Depth Estimation (Q)
64% 3510
32.2 IPS
 
Style Transfer (SP)
89% 3604
4.68 IPS
 
Style Transfer (HP)
89% 3614
4.69 IPS
 
Style Transfer (Q)
98% 8705
11.2 IPS
 
Image Super-Resolution (SP)
100% 813
30.0 IPS
 
Image Super-Resolution (HP)
100% 819
30.2 IPS
 
Image Super-Resolution (Q)
97% 2090
77.4 IPS
 
Text Classification (SP)
100% 521
695.2 IPS
 
Text Classification (HP)
100% 515
687.2 IPS
 
Text Classification (Q)
88% 971
1.31 KIPS
 
Machine Translation (SP)
100% 757
13.0 IPS
 
Machine Translation (HP)
100% 744
12.8 IPS
 
Machine Translation (Q)
50% 478
17.0 IPS
 

Compare

Set Baseline Geekbench 6 now available