Puzzle Solving on Sokoban Simple
2.304ScoreFreshPER
Evaluation Results
| Method | Links | |
|---|---|---|
| FreshPERType=LLM2026.04 | 2.304 | |
| Standard PERType=LLM2026.04 | 0.907 | |
| On-PolicyType=LLM2026.04 | 0.493 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| FreshPERType=LLM2026.04 | 2.304 | |
| Standard PERType=LLM2026.04 | 0.907 | |
| On-PolicyType=LLM2026.04 | 0.493 |