List your company

Classification on Spaceship Titanic

62.55Leaderboard PercentileHierarchical MCTS
-2.50214.386531.27548.1635Nov 29, 2025

Evaluation results

MethodLinks
Hierarchical MCTSBase LLM=GPT-4o2025.1162.55
MCTS-ShapedBase Model=GPT-4.1-mini2025.1162.11
MCTS-ShapedBase LLM=GPT-4o2025.1159.44
ReActBase LLM=GPT-4o2025.1139.54
MCTS-OutcomeBase LLM=GPT-4o2025.1122.88
ReActBase Model=GPT-4.1-mini2025.110
LATSBase Model=GPT-4.1-mini2025.110
MCTS-OutcomeBase Model=GPT-4.1-mini2025.110
Hierarchical MCTSBase Model=GPT-4.1-mini2025.110
LATSBase LLM=GPT-4o2025.110