Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Embodied Household Planning on ALFWorld
Loading...
87.5
Success Rate
TRIAGE
38.828
51.464
64.1
76.736
Jun 30, 2026
Success Rate
Updated 24d ago
Evaluation Results
Method
Method
Links
Success Rate
TRIAGE
Model=Qwen2.5-7B-Instr...
2026.06
87.5
TRIAGE
Model=Qwen2.5-7B-Instr...
2026.06
83.1
GRPO
Model=Qwen2.5-7B-Instruct
2026.06
79.6
TRIAGE
Model=Qwen2.5-7B-Instr...
2026.06
76.8
TRIAGE
Model=Qwen3-1.7B-Instr...
2026.06
56.4
TRIAGE
Model=Qwen3-1.7B-Instr...
2026.06
51.8
GRPO
Model=Qwen3-1.7B-Instruct
2026.06
45.2
TRIAGE
Model=Qwen3-1.7B-Instr...
2026.06
40.7
Feedback
Search any
task
Search any
task