Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic Task Accuracy on ALFWorld
Loading...
79.1
Task Accuracy
Hard final
56.636
62.468
68.3
74.132
Jun 18, 2026
Task Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Task Accuracy
Hard final
Skill Setting=Hard final
2026.06
79.1
SOFTSKILL
Skill Setting=Val-sele...
2026.06
71.6
Oracle grid best
Skill Setting=Oracle g...
2026.06
71.6
Hard initial
Skill Setting=Hard ini...
2026.06
64.9
No skill
Skill Setting=No skill
2026.06
57.5
Feedback
Search any
task
Search any
task