Geekbench ML Score

2541
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 29 2025 02:52 PM
Views 6

System Information

System Information
Operating System iOS 26.0
Model iPhone15,2
Model IDiPhone15,2
Motherboard D73AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.44 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.53 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2880
308.5 IPS
 
Image Classification (F16)
100% 4557
488.3 IPS
 
Image Classification (I8)
81% 746
79.9 IPS
 
Image Segmentation (F32)
100% 6522
40.3 IPS
 
Image Segmentation (F16)
100% 8875
54.8 IPS
 
Image Segmentation (I8)
89% 1366
8.44 IPS
 
Pose Estimation (F32)
100% 2579
10.4 IPS
 
Pose Estimation (F16)
100% 5121
20.7 IPS
 
Pose Estimation (I8)
80% 258
1.05 IPS
 
Object Detection (F32)
100% 3313
116.3 IPS
 
Object Detection (F16)
100% 3645
127.9 IPS
 
Object Detection (I8)
52% 1070
37.5 IPS
 
Face Detection (F32)
100% 6068
69.7 IPS
 
Face Detection (F16)
97% 10138
116.5 IPS
 
Face Detection (I8)
75% 1046
12.0 IPS
 
Text Classification (F32)
100% 2117
837.1 IPS
 
Text Classification (F16)
100% 2094
828.2 IPS
 
Machine Translation (F32)
100% 2258
348.0 IPS
 
Machine Translation (F16)
100% 2266
349.2 IPS
 

Compare

Set Baseline Geekbench 6 now available