Geekbench AI Score

29346
Single Precision Score
46626
Half Precision Score
43774
Quantized Score
Geekbench AI 1.7.0 for macOS AArch64

Result Information

User geekgrunt
Upload Date March 26 2026 01:54 PM
Views 7

System Information

AI Information
Framework Core ML
Backend GPU
Device Apple M5 Max
System Information
Operating System macOS 26.4 (Build 25E246)
Model Mac17,6
Model IDMac17,6
Motherboard Mac17,6
CPU Information
Name Apple M5 Max
Topology 1 Processor, 18 Cores
Identifier Apple M5 Max
Base Frequency 4.60 GHz
Cluster 16 Cores
Cluster 212 Cores
Memory Information
Size 64.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 10411
1.94 KIPS
 
Image Classification (HP)
100% 13649
2.54 KIPS
 
Image Classification (Q)
97% 11984
2.24 KIPS
 
Image Segmentation (SP)
100% 28037
454.5 IPS
 
Image Segmentation (HP)
100% 42657
691.5 IPS
 
Image Segmentation (Q)
99% 39192
635.3 IPS
 
Pose Estimation (SP)
100% 130700
152.5 IPS
 
Pose Estimation (HP)
100% 336011
392.1 IPS
 
Pose Estimation (Q)
95% 289719
339.6 IPS
 
Object Detection (SP)
100% 10261
813.9 IPS
 
Object Detection (HP)
100% 14865
1.18 KIPS
 
Object Detection (Q)
94% 14897
1.19 KIPS
 
Face Detection (SP)
100% 49944
593.4 IPS
 
Face Detection (HP)
100% 72620
862.9 IPS
 
Face Detection (Q)
100% 65342
776.4 IPS
 
Depth Estimation (SP)
100% 53448
411.8 IPS
 
Depth Estimation (HP)
99% 87887
677.1 IPS
 
Depth Estimation (Q)
86% 86957
678.9 IPS
 
Style Transfer (SP)
100% 264879
340.5 IPS
 
Style Transfer (HP)
100% 551470
708.9 IPS
 
Style Transfer (Q)
96% 613905
792.2 IPS
 
Image Super-Resolution (SP)
100% 34752
1.28 KIPS
 
Image Super-Resolution (HP)
100% 52264
1.93 KIPS
 
Image Super-Resolution (Q)
99% 42674
1.58 KIPS
 
Text Classification (SP)
100% 5937
7.92 KIPS
 
Text Classification (HP)
100% 10174
13.6 KIPS
 
Text Classification (Q)
92% 10024
13.5 KIPS
 
Machine Translation (SP)
100% 8295
142.9 IPS
 
Machine Translation (HP)
100% 8923
153.7 IPS
 
Machine Translation (Q)
98% 8542
147.6 IPS
 

Compare

Set Baseline Geekbench 6 now available