Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LTL Instruction Following on ChessWorld finite-horizon phi7 (test)
Loading...
91.9
Success Rate
DeepLTL
80.356
83.353
86.35
89.347
Dec 2, 2025
Success Rate
J(pi)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
J(pi)
DeepLTL
Horizon=Finite
2025.12
91.9
0.897
LTL-GNN
Horizon=Finite
2025.12
91
0.888
Transformer
Horizon=Finite
2025.12
80.8
0.785
Feedback
Search any
task
Search any
task