Geekbench AI Score

3494
Single Precision Score
28231
Half Precision Score
31402
Quantized Score
Geekbench AI 1.7.0 for macOS AArch64

Result Information

User mduncanvm
Upload Date March 13 2026 04:37 PM
Views 6

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M2
System Information
Operating System macOS 26.4 (Build 25E5233c)
Model MacBook Air (15-inch, 2023)
Model IDMac14,15
Motherboard Mac14,15
CPU Information
Name Apple M2
Topology 1 Processor, 8 Cores
Identifier Apple M2
Base Frequency 3.48 GHz
Cluster 14 Cores
Cluster 24 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1310
243.6 IPS
 
Image Classification (HP)
100% 15213
2.83 KIPS
 
Image Classification (Q)
97% 15876
2.96 KIPS
 
Image Segmentation (SP)
100% 1443
23.4 IPS
 
Image Segmentation (HP)
100% 19739
320.0 IPS
 
Image Segmentation (Q)
99% 24438
396.2 IPS
 
Pose Estimation (SP)
100% 6203
7.24 IPS
 
Pose Estimation (HP)
100% 105592
123.2 IPS
 
Pose Estimation (Q)
95% 105309
123.4 IPS
 
Object Detection (SP)
100% 1425
113.0 IPS
 
Object Detection (HP)
99% 15786
1.26 KIPS
 
Object Detection (Q)
89% 17757
1.42 KIPS
 
Face Detection (SP)
100% 3051
36.3 IPS
 
Face Detection (HP)
100% 35078
416.8 IPS
 
Face Detection (Q)
100% 48155
572.2 IPS
 
Depth Estimation (SP)
100% 5397
41.6 IPS
 
Depth Estimation (HP)
99% 87129
671.3 IPS
 
Depth Estimation (Q)
85% 112246
878.1 IPS
 
Style Transfer (SP)
100% 18009
23.2 IPS
 
Style Transfer (HP)
100% 205434
264.1 IPS
 
Style Transfer (Q)
96% 189484
244.5 IPS
 
Image Super-Resolution (SP)
100% 3716
137.2 IPS
 
Image Super-Resolution (HP)
100% 39262
1.45 KIPS
 
Image Super-Resolution (Q)
99% 46918
1.73 KIPS
 
Text Classification (SP)
100% 4076
5.44 KIPS
 
Text Classification (HP)
100% 6214
8.29 KIPS
 
Text Classification (Q)
93% 6113
8.20 KIPS
 
Machine Translation (SP)
100% 3621
62.4 IPS
 
Machine Translation (HP)
100% 4195
72.3 IPS
 
Machine Translation (Q)
98% 4376
75.6 IPS
 

Compare

Set Baseline Geekbench 6 now available