Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Interactive Embodied Instruction Following on ALFWorld In-domain
Loading...
97
Score
Task-Perturbed NLL Optimization
81.4
85.45
89.5
93.55
Jun 25, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Task-Perturbed NLL Optimization
Backbone=Qwen3-8B
2026.06
97
GRPO
Backbone=Qwen3-8B
2026.06
95
Task-Perturbed NLL Optimization
Backbone=Qwen3-4B
2026.06
86
GRPO
Backbone=Qwen3-4B
2026.06
82
Feedback
Search any
task
Search any
task