Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Interactive Decision-Making on ALFWorld (OOD)
Loading...
56.43
Success Rate
Multi2
3.078
16.929
30.78
44.631
Jun 2, 2026
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
Multi2
Base Model=Llama-3.1 8...
2026.06
56.43
Multi2
Base Model=Mistral 7B,...
2026.06
50.71
Multi2
Base Model=Qwen-2.5 3B...
2026.06
49.29
Glider
Base Model=Mistral 7B,...
2026.06
45.71
Glider
Base Model=Qwen-2.5 3B...
2026.06
41.43
Glider
Base Model=Llama-3.1 8...
2026.06
37.86
Reflexion
Base Model=Llama-3.1 8...
2026.06
29.29
Reflexion
Base Model=Qwen-2.5 3B...
2026.06
25.36
Reflexion
Base Model=Mistral 7B,...
2026.06
22.83
ADaPT
Base Model=Qwen-2.5 3B...
2026.06
10.26
GRPO
Base Model=Llama-3.1 8...
2026.06
7.5
ReAct
Base Model=Llama-3.1 8...
2026.06
7.46
GRPO
Base Model=Mistral 7B,...
2026.06
7.1
ReAct
Base Model=Mistral 7B,...
2026.06
6.72
GRPO
Base Model=Qwen-2.5 3B...
2026.06
6.43
ADaPT
Base Model=Llama-3.1 8...
2026.06
6.41
ReAct
Base Model=Qwen-2.5 3B...
2026.06
5.22
ADaPT
Base Model=Mistral 7B,...
2026.06
5.13
Feedback
Search any
task
Search any
task