Geekbench AI Score

908
Single Precision Score
903
Half Precision Score
2072
Quantized Score
Geekbench AI 1.2.0 for Android AArch64

Result Information

Upload Date January 14 2025 06:43 PM
Views 19

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device MediaTek Dimensity 7300
System Information
Operating System Android 14
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 7.28 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 466
86.7 IPS
 
Image Classification (HP)
100% 432
80.4 IPS
 
Image Classification (Q)
100% 1437
267.2 IPS
 
Image Segmentation (SP)
100% 527
8.54 IPS
 
Image Segmentation (HP)
100% 531
8.61 IPS
 
Image Segmentation (Q)
98% 1730
28.1 IPS
 
Pose Estimation (SP)
100% 2014
2.35 IPS
 
Pose Estimation (HP)
100% 1995
2.33 IPS
 
Pose Estimation (Q)
84% 3915
4.64 IPS
 
Object Detection (SP)
100% 458
36.3 IPS
 
Object Detection (HP)
100% 451
35.8 IPS
 
Object Detection (Q)
83% 1430
115.5 IPS
 
Face Detection (SP)
100% 1034
12.3 IPS
 
Face Detection (HP)
100% 1041
12.4 IPS
 
Face Detection (Q)
95% 3499
41.8 IPS
 
Depth Estimation (SP)
100% 1381
10.6 IPS
 
Depth Estimation (HP)
99% 1478
11.4 IPS
 
Depth Estimation (Q)
64% 3519
32.2 IPS
 
Style Transfer (SP)
89% 3606
4.68 IPS
 
Style Transfer (HP)
89% 3591
4.66 IPS
 
Style Transfer (Q)
98% 8840
11.4 IPS
 
Image Super-Resolution (SP)
100% 826
30.5 IPS
 
Image Super-Resolution (HP)
100% 820
30.3 IPS
 
Image Super-Resolution (Q)
97% 2111
78.2 IPS
 
Text Classification (SP)
100% 519
692.2 IPS
 
Text Classification (HP)
100% 516
689.0 IPS
 
Text Classification (Q)
88% 963
1.30 KIPS
 
Machine Translation (SP)
100% 762
13.1 IPS
 
Machine Translation (HP)
100% 749
12.9 IPS
 
Machine Translation (Q)
50% 475
16.9 IPS
 

Compare

Set Baseline Geekbench 6 now available