Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LTL Instruction Following on LetterWorld Finite-horizon
Loading...
100
Success Rate (SR)
DEEPLTL
45.92
59.96
74
88.04
Feb 6, 2026
Success Rate (SR)
Average States Traversed (µstates)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate (SR)
Average States Traversed (µstates)
DEEPLTL
Task Formula=(F((a ∨ c...
2026.02
100
-
SEMLTL
Task Formula=(F((a ∨ c...
2026.02
100
3.04
DEEPLTL
Task Formula=F(a ∧ (¬b...
2026.02
100
-
SEMLTL
Task Formula=F(a ∧ (¬b...
2026.02
100
4.2
SEMLTL
Task Formula=(F d) ∧ (...
2026.02
96
5.23
DEEPLTL
Task Formula=¬a U (b ∧...
2026.02
95
-
SEMLTL
Task Formula=¬a U (b ∧...
2026.02
95
4.01
DEEPLTL
Task Formula=(F d) ∧ (...
2026.02
95
-
LTL2ACTION
Task Formula=(F d) ∧ (...
2026.02
84
-
LTL2ACTION
Task Formula=¬a U (b ∧...
2026.02
73
-
LTL2ACTION
Task Formula=F(a ∧ (¬b...
2026.02
62
-
LTL2ACTION
Task Formula=(F((a ∨ c...
2026.02
48
-
Feedback
Search any
task
Search any
task