Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Hierarchical Crafting on TextCraft
Loading...
88.9
Score
Best-of-15 (ReAct)
7.052
28.301
49.55
70.799
Jun 3, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Best-of-15 (ReAct)
Policy Model=GPT-5.1
2026.06
88.9
AMC (ReAct)
Policy Model=GPT-4.1-m...
2026.06
85.2
AMC (ReAct)
Policy Model=GPT-5.1,...
2026.06
79
Best-of-15 (ReAct)
Policy Model=GPT-4.1-mini
2026.06
72.8
ReAct
Policy Model=GPT-5.1
2026.06
69.1
AMC (ReAct)
Policy Model=Llama-3.2...
2026.06
54.3
ReAct
Policy Model=GPT-4.1-mini
2026.06
43.2
Best-of-15 (ReAct)
Policy Model=Llama-3.2...
2026.06
29.6
ReAct
Policy Model=Llama-3.2...
2026.06
10.2
Feedback
Search any
task
Search any
task