ChessWorld
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| LTL Instruction Following | ChessWorld finite-horizon phi7 (test) | Success Rate91.9 | 3 | |
| LTL Instruction Following | ChessWorld finite-horizon, phi6 (test) | Success Rate93.6 | 3 | |
| LTL Instruction Following | ChessWorld finite-horizon phi5 (test) | Success Rate74.3 | 3 | |
| LTL Instruction Following | ChessWorld finite-horizon phi4 (test) | SR0.927 | 3 | |
| LTL Instruction Following | ChessWorld finite-horizon phi3 (test) | SR82.6 | 3 | |
| LTL Instruction Following | ChessWorld finite-horizon phi2 (test) | Success Rate95.2 | 3 | |
| LTL Instruction Following | ChessWorld finite-horizon phi1 (test) | SR99.3 | 3 | |
| LTL Instruction Following | ChessWorld infinite-horizon ϕ∞ 2 | Success Rate0.767 | 3 | |
| LTL Instruction Following | ChessWorld infinite-horizon ϕ∞ 1 | Success Rate86 | 3 | |
| LTL Instruction Following | ChessWorld infinite-horizon ϕ∞ GF | Success Rate95.7 | 3 |
Showing 10 of 10 rows