Geekbench AI Score

8935
Single Precision Score
9798
Half Precision Score
8682
Quantized Score
Geekbench AI 1.6.0 for macOS AArch64

Result Information

User Jolo
Upload Date February 14 2026 07:39 PM
Views 7

System Information

AI Information
Framework Core ML
Backend GPU
Device Apple M1 Pro
System Information
Operating System macOS 26.3 (Build 25D125)
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 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 3750
697.4 IPS
 
Image Classification (HP)
100% 3779
702.8 IPS
 
Image Classification (Q)
94% 3633
679.0 IPS
 
Image Segmentation (SP)
100% 6814
110.5 IPS
 
Image Segmentation (HP)
100% 6821
110.6 IPS
 
Image Segmentation (Q)
99% 6546
106.1 IPS
 
Pose Estimation (SP)
100% 29828
34.8 IPS
 
Pose Estimation (HP)
100% 32271
37.7 IPS
 
Pose Estimation (Q)
96% 30998
36.3 IPS
 
Object Detection (SP)
100% 3698
293.3 IPS
 
Object Detection (HP)
100% 3864
306.5 IPS
 
Object Detection (Q)
91% 3670
293.3 IPS
 
Face Detection (SP)
100% 13665
162.4 IPS
 
Face Detection (HP)
100% 14058
167.0 IPS
 
Face Detection (Q)
100% 12841
152.6 IPS
 
Depth Estimation (SP)
100% 17391
134.0 IPS
 
Depth Estimation (HP)
99% 16279
125.4 IPS
 
Depth Estimation (Q)
85% 15540
121.5 IPS
 
Style Transfer (SP)
100% 50191
64.5 IPS
 
Style Transfer (HP)
100% 59680
76.7 IPS
 
Style Transfer (Q)
96% 58228
75.1 IPS
 
Image Super-Resolution (SP)
100% 10406
384.3 IPS
 
Image Super-Resolution (HP)
100% 11014
406.7 IPS
 
Image Super-Resolution (Q)
99% 9617
355.1 IPS
 
Text Classification (SP)
100% 2375
3.17 KIPS
 
Text Classification (HP)
99% 4162
5.56 KIPS
 
Text Classification (Q)
93% 4131
5.54 KIPS
 
Machine Translation (SP)
100% 3906
67.3 IPS
 
Machine Translation (HP)
100% 4054
69.8 IPS
 
Machine Translation (Q)
98% 1949
33.7 IPS
 

Compare

Set Baseline Geekbench 6 now available