Geekbench ML Score

540
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 13 2025 12:35 PM
Views 6

System Information

System Information
Operating System iOS 18.2.1
Model iPhone XS
Model IDiPhone11,2
Motherboard D321AP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 3.69 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 463
49.6 IPS
 
Image Classification (F16)
100% 459
49.2 IPS
 
Image Classification (I8)
81% 179
19.2 IPS
 
Image Segmentation (F32)
100% 769
4.75 IPS
 
Image Segmentation (F16)
100% 754
4.66 IPS
 
Image Segmentation (I8)
89% 955
5.90 IPS
 
Pose Estimation (F32)
100% 237
0.96 IPS
 
Pose Estimation (F16)
100% 232
0.94 IPS
 
Pose Estimation (I8)
80% 259
1.05 IPS
 
Object Detection (F32)
100% 677
23.7 IPS
 
Object Detection (F16)
100% 674
23.6 IPS
 
Object Detection (I8)
52% 527
18.5 IPS
 
Face Detection (F32)
100% 824
9.47 IPS
 
Face Detection (F16)
100% 841
9.66 IPS
 
Face Detection (I8)
75% 594
6.82 IPS
 
Text Classification (F32)
100% 745
294.5 IPS
 
Text Classification (F16)
100% 400
158.1 IPS
 
Machine Translation (F32)
100% 987
152.1 IPS
 
Machine Translation (F16)
100% 970
149.4 IPS
 

Compare

Set Baseline Geekbench 6 now available