Geekbench ML Score

3347
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date July 12 2025 04:45 AM
Views 2

System Information

System Information
Operating System iOS 18.5
Model iPhone17,1
Model IDiPhone17,1
Motherboard D93AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 4.04 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.47 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3649
391.0 IPS
 
Image Classification (F16)
100% 7236
775.4 IPS
 
Image Classification (I8)
81% 925
99.1 IPS
 
Image Segmentation (F32)
100% 7046
43.5 IPS
 
Image Segmentation (F16)
100% 12493
77.2 IPS
 
Image Segmentation (I8)
89% 1622
10.0 IPS
 
Pose Estimation (F32)
100% 2512
10.2 IPS
 
Pose Estimation (F16)
100% 6686
27.1 IPS
 
Pose Estimation (I8)
80% 281
1.14 IPS
 
Object Detection (F32)
100% 4528
158.9 IPS
 
Object Detection (F16)
100% 4490
157.6 IPS
 
Object Detection (I8)
52% 1271
44.6 IPS
 
Face Detection (F32)
100% 7048
81.0 IPS
 
Face Detection (F16)
97% 14384
165.3 IPS
 
Face Detection (I8)
75% 1281
14.7 IPS
 
Text Classification (F32)
100% 3423
1.35 KIPS
 
Text Classification (F16)
100% 2837
1.12 KIPS
 
Machine Translation (F32)
100% 4166
642.1 IPS
 
Machine Translation (F16)
100% 4171
642.8 IPS
 

Compare

Set Baseline Geekbench 6 now available