Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Step Completion on CoSPlan Maze-E
Loading...
46.1
Accuracy
GPT-4o
18.956
26.003
33.05
40.097
Dec 11, 2025
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
GPT-4o
Reasoning Strategy=Sce...
2025.12
46.1
GPT-4o
Reasoning Strategy=Cha...
2025.12
45.6
Intern-VLM
Reasoning Strategy=Sce...
2025.12
41.2
Intern-VLM
Reasoning Strategy=Cha...
2025.12
35.8
Qwen2 VL-8B
Reasoning Strategy=Sce...
2025.12
28.3
Qwen2 VL-8B
Reasoning Strategy=Cha...
2025.12
27.9
Qwen2 VL-8B
Reasoning Strategy=Van...
2025.12
26.5
CoG-VLM
Reasoning Strategy=Sce...
2025.12
26.5
CoG-VLM
Reasoning Strategy=Cha...
2025.12
25.9
CoG-VLM
Reasoning Strategy=Van...
2025.12
25.1
Janus-pro-7B
Reasoning Strategy=Sce...
2025.12
21.7
Intern-VLM
Reasoning Strategy=Van...
2025.12
21.6
Janus-pro-7B
Reasoning Strategy=Van...
2025.12
20.4
Janus-pro-7B
Reasoning Strategy=Cha...
2025.12
20.2
Random
2025.12
20
Feedback
Search any
task
Search any
task