Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Agentic Task Success on Baba Is AI
Loading...
38
Success Rate
Dynamic Cheatsheet
8.36
16.055
23.75
31.445
Feb 8, 2026
Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate
Dynamic Cheatsheet
Foundation Model=GPT-5...
2026.02
38
ALMA
Foundation Model=GPT-5...
2026.02
33.3
Trajectory Retrieval
Foundation Model=GPT-5...
2026.02
30.9
G-Memory
Foundation Model=GPT-5...
2026.02
26.2
No Memory
Foundation Model=GPT-5...
2026.02
21.4
Reasoning Bank
Foundation Model=GPT-5...
2026.02
21.4
Trajectory Retrieval
Foundation Model=GPT-5...
2026.02
19
ALMA
Foundation Model=GPT-5...
2026.02
19
G-Memory
Foundation Model=GPT-5...
2026.02
14.3
No Memory
Foundation Model=GPT-5...
2026.02
9.5
Reasoning Bank
Foundation Model=GPT-5...
2026.02
9.5
Dynamic Cheatsheet
Foundation Model=GPT-5...
2026.02
9.5
Feedback
Search any
task
Search any
task