Geekbench AI Score

1736
Single Precision Score
12434
Half Precision Score
9980
Quantized Score
Geekbench AI 1.5.0 for macOS AArch64

Result Information

User bytespider
Upload Date December 17 2025 09:30 AM
Views 10

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M1
System Information
Operating System macOS 14.8.1 (Build 23J30)
Model MacBook Pro (13-inch Late 2020)
Model IDMacBookPro17,1
Motherboard MacBookPro17,1
CPU Information
Name Apple M1
Topology 1 Processor, 8 Cores
Identifier Apple M1
Base Frequency 3.19 GHz
Cluster 14 Cores
Cluster 24 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 959
178.3 IPS
 
Image Classification (HP)
100% 6398
1.19 KIPS
 
Image Classification (Q)
96% 5739
1.07 KIPS
 
Image Segmentation (SP)
100% 644
10.4 IPS
 
Image Segmentation (HP)
100% 4254
69.0 IPS
 
Image Segmentation (Q)
99% 484
7.84 IPS
 
Pose Estimation (SP)
100% 5685
6.63 IPS
 
Pose Estimation (HP)
100% 67316
78.5 IPS
 
Pose Estimation (Q)
95% 65602
76.9 IPS
 
Object Detection (SP)
100% 1051
83.3 IPS
 
Object Detection (HP)
99% 7181
571.2 IPS
 
Object Detection (Q)
93% 6538
521.7 IPS
 
Face Detection (SP)
100% 1668
19.8 IPS
 
Face Detection (HP)
100% 12194
144.9 IPS
 
Face Detection (Q)
100% 11803
140.2 IPS
 
Depth Estimation (SP)
100% 3101
23.9 IPS
 
Depth Estimation (HP)
99% 44814
345.3 IPS
 
Depth Estimation (Q)
85% 52073
406.9 IPS
 
Style Transfer (SP)
100% 9705
12.5 IPS
 
Style Transfer (HP)
100% 118865
152.8 IPS
 
Style Transfer (Q)
96% 112455
145.1 IPS
 
Image Super-Resolution (SP)
100% 2457
90.7 IPS
 
Image Super-Resolution (HP)
100% 17951
662.8 IPS
 
Image Super-Resolution (Q)
99% 20725
765.3 IPS
 
Text Classification (SP)
100% 405
540.0 IPS
 
Text Classification (HP)
100% 2504
3.34 KIPS
 
Text Classification (Q)
93% 2521
3.38 KIPS
 
Machine Translation (SP)
100% 1351
23.3 IPS
 
Machine Translation (HP)
100% 2300
39.6 IPS
 
Machine Translation (Q)
98% 2279
39.4 IPS
 

Compare

Set Baseline Geekbench 6 now available