Geekbench AI Score

3304
Single Precision Score
26637
Half Precision Score
29208
Quantized Score
Geekbench AI 1.5.0 for macOS AArch64

Result Information

User galois1811
Upload Date December 14 2025 03:12 AM
Views 5

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M2
System Information
Operating System macOS 26.1 (Build 25B78)
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 3.49 GHz
Cluster 14 Cores
Cluster 24 Cores
Memory Information
Size 8.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1293
240.5 IPS
 
Image Classification (HP)
100% 14674
2.73 KIPS
 
Image Classification (Q)
96% 15892
2.97 KIPS
 
Image Segmentation (SP)
100% 1399
22.7 IPS
 
Image Segmentation (HP)
100% 19543
316.8 IPS
 
Image Segmentation (Q)
99% 24168
391.8 IPS
 
Pose Estimation (SP)
100% 6303
7.35 IPS
 
Pose Estimation (HP)
100% 103232
120.5 IPS
 
Pose Estimation (Q)
95% 105245
123.4 IPS
 
Object Detection (SP)
100% 1402
111.2 IPS
 
Object Detection (HP)
99% 15786
1.26 KIPS
 
Object Detection (Q)
91% 17147
1.37 KIPS
 
Face Detection (SP)
100% 3074
36.5 IPS
 
Face Detection (HP)
100% 34341
408.0 IPS
 
Face Detection (Q)
100% 43622
518.3 IPS
 
Depth Estimation (SP)
100% 5458
42.0 IPS
 
Depth Estimation (HP)
99% 86862
669.2 IPS
 
Depth Estimation (Q)
85% 107958
843.6 IPS
 
Style Transfer (SP)
100% 18114
23.3 IPS
 
Style Transfer (HP)
100% 205585
264.3 IPS
 
Style Transfer (Q)
96% 190836
246.3 IPS
 
Image Super-Resolution (SP)
100% 3739
138.1 IPS
 
Image Super-Resolution (HP)
100% 38694
1.43 KIPS
 
Image Super-Resolution (Q)
99% 43106
1.59 KIPS
 
Text Classification (SP)
100% 2346
3.13 KIPS
 
Text Classification (HP)
99% 3871
5.17 KIPS
 
Text Classification (Q)
93% 3851
5.17 KIPS
 
Machine Translation (SP)
100% 3648
62.8 IPS
 
Machine Translation (HP)
100% 4190
72.2 IPS
 
Machine Translation (Q)
98% 4371
75.5 IPS
 

Compare

Set Baseline Geekbench 6 now available