Geekbench AI Score

3200
Single Precision Score
16129
Half Precision Score
15479
Quantized Score
Geekbench AI 1.3.0 for macOS AArch64

Result Information

User slavatsarev
Upload Date March 23 2025 09:48 PM
Views 8

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M1
System Information
Operating System macOS 15.3.2 (Build 24D81)
Model MacBook Air (Late 2020)
Model IDMacBookAir10,1
Motherboard MacBookAir10,1
CPU Information
Name Apple M1
Topology 1 Processor, 8 Cores
Identifier Apple M1
Base Frequency 3.20 GHz
Cluster 14 Cores
Cluster 24 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1395
259.4 IPS
 
Image Classification (HP)
100% 6528
1.21 KIPS
 
Image Classification (Q)
96% 6130
1.14 KIPS
 
Image Segmentation (SP)
100% 1375
22.3 IPS
 
Image Segmentation (HP)
100% 9830
159.4 IPS
 
Image Segmentation (Q)
99% 10150
164.5 IPS
 
Pose Estimation (SP)
100% 6475
7.56 IPS
 
Pose Estimation (HP)
100% 69114
80.6 IPS
 
Pose Estimation (Q)
95% 65632
76.9 IPS
 
Object Detection (SP)
100% 1509
119.7 IPS
 
Object Detection (HP)
99% 7511
597.5 IPS
 
Object Detection (Q)
91% 6787
542.3 IPS
 
Face Detection (SP)
100% 2968
35.3 IPS
 
Face Detection (HP)
100% 16674
198.1 IPS
 
Face Detection (Q)
100% 13338
158.5 IPS
 
Depth Estimation (SP)
100% 5749
44.3 IPS
 
Depth Estimation (HP)
99% 48754
375.6 IPS
 
Depth Estimation (Q)
85% 49080
383.5 IPS
 
Style Transfer (SP)
100% 16541
21.3 IPS
 
Style Transfer (HP)
100% 121680
156.4 IPS
 
Style Transfer (Q)
96% 115708
149.3 IPS
 
Image Super-Resolution (SP)
100% 3716
137.2 IPS
 
Image Super-Resolution (HP)
100% 24026
887.2 IPS
 
Image Super-Resolution (Q)
99% 24826
916.7 IPS
 
Text Classification (SP)
100% 2339
3.12 KIPS
 
Text Classification (HP)
100% 4130
5.51 KIPS
 
Text Classification (Q)
93% 4075
5.47 KIPS
 
Machine Translation (SP)
100% 2456
42.3 IPS
 
Machine Translation (HP)
100% 3645
62.8 IPS
 
Machine Translation (Q)
98% 3720
64.3 IPS
 

Compare

Set Baseline Geekbench 6 now available