Geekbench AI Score

3081
Single Precision Score
14868
Half Precision Score
14351
Quantized Score
Geekbench AI 1.7.0 for macOS AArch64

Result Information

User samuelgibbs
Upload Date March 16 2026 03:32 PM
Views 20

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M1
System Information
Operating System macOS 26.3.1 (Build 25D2128)
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 8.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1295
240.9 IPS
 
Image Classification (HP)
100% 6276
1.17 KIPS
 
Image Classification (Q)
96% 5971
1.12 KIPS
 
Image Segmentation (SP)
100% 1302
21.1 IPS
 
Image Segmentation (HP)
100% 9101
147.5 IPS
 
Image Segmentation (Q)
99% 9227
149.6 IPS
 
Pose Estimation (SP)
100% 6007
7.01 IPS
 
Pose Estimation (HP)
100% 67632
78.9 IPS
 
Pose Estimation (Q)
95% 64753
75.9 IPS
 
Object Detection (SP)
100% 1390
110.3 IPS
 
Object Detection (HP)
99% 7025
558.8 IPS
 
Object Detection (Q)
91% 6318
504.8 IPS
 
Face Detection (SP)
100% 2980
35.4 IPS
 
Face Detection (HP)
100% 14236
169.2 IPS
 
Face Detection (Q)
100% 12770
151.7 IPS
 
Depth Estimation (SP)
100% 5453
42.0 IPS
 
Depth Estimation (HP)
99% 45812
353.0 IPS
 
Depth Estimation (Q)
85% 46273
361.6 IPS
 
Style Transfer (SP)
100% 16487
21.2 IPS
 
Style Transfer (HP)
100% 121882
156.7 IPS
 
Style Transfer (Q)
96% 114370
147.6 IPS
 
Image Super-Resolution (SP)
100% 3447
127.3 IPS
 
Image Super-Resolution (HP)
100% 24164
892.3 IPS
 
Image Super-Resolution (Q)
99% 24233
894.8 IPS
 
Text Classification (SP)
100% 2393
3.19 KIPS
 
Text Classification (HP)
99% 4220
5.63 KIPS
 
Text Classification (Q)
93% 4105
5.51 KIPS
 
Machine Translation (SP)
100% 2479
42.7 IPS
 
Machine Translation (HP)
100% 2401
41.4 IPS
 
Machine Translation (Q)
98% 2446
42.3 IPS
 

Compare

Set Baseline Geekbench 6 now available