Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Visual Spatial Reasoning on MMSI-Bench
Loading...
36.6
Cam-Cam Accuracy
GPT-4.1
30.88
32.365
33.85
35.335
Feb 9, 2026
Cam-Cam Accuracy
Obj-Obj Accuracy
Reg-Reg Accuracy
Cam-Obj Accuracy
Obj-Reg Accuracy
Cam-Reg Accuracy
Measurement Score
Appearance Score
Camera Score
Object Score
MSR (Mean Spatial Reasoning)
Average Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Cam-Cam Accuracy
Obj-Obj Accuracy
Reg-Reg Accuracy
Cam-Obj Accuracy
Obj-Reg Accuracy
Cam-Reg Accuracy
Measurement Score
Appearance Score
Camera Score
Object Score
MSR (Mean Spatial Reasoning)
Average Score
GPT-4.1
Model=GPT-4.1
2026.02
36.6
26.6
27.2
29.1
36.5
27.7
37.5
24.2
36.5
32.9
28.8
30.9
GPT-4o
Model=GPT-4o
2026.02
34.4
24.5
23.5
19.8
37.6
27.7
32.8
31.8
35.1
36.8
30.8
30.3
AVIC
Backbone=GPT-4.1
2026.02
32.2
24.4
27.1
26.7
44.7
32.5
51.5
37.8
33.7
36.8
32.3
33.8
AVIC
Backbone=GPT-4o
2026.02
31.1
29.9
27.8
25
36.5
36.5
51.2
39.7
31.6
32.3
28.2
32.3
Feedback
Search any
task
Search any
task