Make Sandwich on BestMan (Hard)
100Success RateMCTS
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| MCTSRobot Types=2 Types, T=02026.06 | 100 | 100 | 21.5 | — | — | |
| DynaHMRC-Qwen3-4BRobot Types=4 Types, T=02026.06 | 77.78 | 83.33 | 26.4 | 22.325 | 2.15 | |
| DynaHMRC-GPT4oRobot Types=2 Types, T=02026.06 | 66.67 | 80.56 | 31.7222 | 25.7778 | 7.8056 | |
| CoELARobot Types=4 Types, T=02026.06 | 66.67 | 72.22 | 28.3333 | 26.8333 | 3.3333 | |
| CoELARobot Types=3 Types, T=02026.06 | 62.96 | 77.28 | 30.6296 | 26.716 | 4.358 | |
| DynaHMRC-GPT4oRobot Types=3 Types, T=02026.06 | 62.96 | 74.94 | 30.5556 | 25.321 | 7.1728 | |
| DynaHMRC-GPT4oRobot Types=4 Types, T=02026.06 | 62.5 | 76.67 | 34.4 | 28.325 | 7.55 | |
| CoELARobot Types=2 Types, T=02026.06 | 61.11 | 80.56 | 29.8889 | 21.6111 | 2.6944 | |
| DynaHMRC-Qwen3-4BRobot Types=3 Types, T=02026.06 | 55.56 | 72.28 | 38.0741 | 28.321 | 4.6173 | |
| DynaHMRC-Qwen3-4BRobot Types=2 Types, T=02026.06 | 44.44 | 62.96 | 37 | 23.8611 | 3.8333 | |
| MCTSRobot Types=3 Types, T=02026.06 | 33.33 | 45.19 | 39.5556 | — | — | |
| MCTS-NoINSRobot Types=2 Types, T=02026.06 | 16.67 | 28.24 | 48 | — | — | |
| MCTS-NoINSRobot Types=3 Types, T=02026.06 | 11.11 | 16.42 | 48.6296 | — | — | |
| MCTS-NoINSRobot Types=4 Types, T=02026.06 | 0 | 0 | 50 | — | — | |
| MCTSRobot Types=4 Types, T=02026.06 | 0 | 11.11 | 50 | — | — |