Geekbench AI Score

4055
Single Precision Score
6832
Half Precision Score
5438
Quantized Score
Geekbench AI 1.7.0 for macOS AArch64

Result Information

User thomasS
Upload Date March 14 2026 11:20 AM
Views 12
Notes 32 GB Ram. CPU Test

System Information

AI Information
Framework Core ML
Backend CPU
Device Apple M2 Max
System Information
Operating System macOS 26.3.1 (Build 25D2128)
Model MacBook Pro (14-inch, 2023)
Model IDMac14,5
Motherboard Mac14,5
CPU Information
Name Apple M2 Max
Topology 1 Processor, 12 Cores
Identifier Apple M2 Max
Base Frequency 3.48 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 32.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1366
254.1 IPS
 
Image Classification (HP)
100% 2265
421.2 IPS
 
Image Classification (Q)
96% 1626
303.7 IPS
 
Image Segmentation (SP)
100% 1632
26.5 IPS
 
Image Segmentation (HP)
100% 2515
40.8 IPS
 
Image Segmentation (Q)
99% 2868
46.5 IPS
 
Pose Estimation (SP)
100% 12099
14.1 IPS
 
Pose Estimation (HP)
100% 26528
31.0 IPS
 
Pose Estimation (Q)
95% 20225
23.7 IPS
 
Object Detection (SP)
100% 1622
128.6 IPS
 
Object Detection (HP)
97% 2700
215.0 IPS
 
Object Detection (Q)
94% 1962
156.4 IPS
 
Face Detection (SP)
100% 3578
42.5 IPS
 
Face Detection (HP)
100% 5974
71.0 IPS
 
Face Detection (Q)
100% 3394
40.3 IPS
 
Depth Estimation (SP)
100% 6038
46.5 IPS
 
Depth Estimation (HP)
98% 11670
90.2 IPS
 
Depth Estimation (Q)
85% 8048
62.9 IPS
 
Style Transfer (SP)
100% 24798
31.9 IPS
 
Style Transfer (HP)
100% 39417
50.7 IPS
 
Style Transfer (Q)
96% 31569
40.7 IPS
 
Image Super-Resolution (SP)
100% 4849
179.1 IPS
 
Image Super-Resolution (HP)
100% 6197
228.8 IPS
 
Image Super-Resolution (Q)
99% 4482
165.5 IPS
 
Text Classification (SP)
100% 2423
3.23 KIPS
 
Text Classification (HP)
99% 4130
5.51 KIPS
 
Text Classification (Q)
93% 4125
5.54 KIPS
 
Machine Translation (SP)
100% 4373
75.3 IPS
 
Machine Translation (HP)
98% 7730
133.6 IPS
 
Machine Translation (Q)
98% 7668
132.5 IPS
 

Compare

Set Baseline Geekbench 6 now available