Share your thoughts, 1 month free Claude Pro on usSee more

Agentic Task Success on Baba Is AI

38Success Rate

Dynamic Cheatsheet

Updated 1mo ago

Evaluation Results

Method	Links
Dynamic Cheatsheet 2026.02		38
ALMA 2026.02		33.3
Trajectory Retrieval 2026.02		30.9
G-Memory 2026.02		26.2
No Memory 2026.02		21.4
Reasoning Bank 2026.02		21.4
Trajectory Retrieval 2026.02		19
ALMA 2026.02		19
G-Memory 2026.02		14.3
No Memory 2026.02		9.5
Reasoning Bank 2026.02		9.5
Dynamic Cheatsheet 2026.02		9.5