Geekbench AI Score

7964
Single Precision Score
8721
Half Precision Score
7683
Quantized Score
Geekbench AI 1.3.0 for macOS AArch64

Result Information

User nagolmas
Upload Date March 27 2025 07:10 PM
Views 15

System Information

AI Information
Framework Core ML
Backend GPU
Device Apple M1 Pro
System Information
Operating System macOS 15.3.2 (Build 24D81)
Model MacBook Pro (14-inch, 2021)
Model IDMacBookPro18,3
Motherboard MacBookPro18,3
CPU Information
Name Apple M1 Pro
Topology 1 Processor, 8 Cores
Identifier Apple M1 Pro
Base Frequency 3.22 GHz
Cluster 16 Cores
Cluster 22 Cores
Memory Information
Size 32.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 3743
696.1 IPS
 
Image Classification (HP)
100% 3820
710.4 IPS
 
Image Classification (Q)
97% 3171
591.8 IPS
 
Image Segmentation (SP)
100% 5835
94.6 IPS
 
Image Segmentation (HP)
100% 5884
95.4 IPS
 
Image Segmentation (Q)
99% 5823
94.4 IPS
 
Pose Estimation (SP)
100% 29819
34.8 IPS
 
Pose Estimation (HP)
100% 31277
36.5 IPS
 
Pose Estimation (Q)
95% 29080
34.1 IPS
 
Object Detection (SP)
100% 3691
292.7 IPS
 
Object Detection (HP)
100% 3905
309.8 IPS
 
Object Detection (Q)
91% 3248
259.5 IPS
 
Face Detection (SP)
100% 13054
155.1 IPS
 
Face Detection (HP)
100% 13492
160.3 IPS
 
Face Detection (Q)
100% 9642
114.6 IPS
 
Depth Estimation (SP)
100% 17318
133.4 IPS
 
Depth Estimation (HP)
99% 17822
137.3 IPS
 
Depth Estimation (Q)
85% 15030
117.5 IPS
 
Style Transfer (SP)
100% 50089
64.4 IPS
 
Style Transfer (HP)
100% 59002
75.8 IPS
 
Style Transfer (Q)
96% 55028
71.0 IPS
 
Image Super-Resolution (SP)
100% 10515
388.3 IPS
 
Image Super-Resolution (HP)
100% 10823
399.7 IPS
 
Image Super-Resolution (Q)
99% 8537
315.2 IPS
 
Text Classification (SP)
100% 2320
3.10 KIPS
 
Text Classification (HP)
100% 4070
5.43 KIPS
 
Text Classification (Q)
93% 3997
5.36 KIPS
 
Machine Translation (SP)
100% 1546
26.6 IPS
 
Machine Translation (HP)
100% 1485
25.6 IPS
 
Machine Translation (Q)
98% 1511
26.1 IPS
 

Compare

Set Baseline Geekbench 6 now available