Make Sandwich on Make Sandwich 3 Types of Robot
92.59Success RateDynaHMRC-Qwen3-4B
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DynaHMRC-Qwen3-4BT=52026.06 | 92.59 | 96.91 | 17.1852 | 12.5679 | 2.0864 | |
| DynaHMRC-GPT4oT=52026.06 | 91.67 | 96.3 | 25.25 | 22.0833 | 4.5556 | |
| COELAT=52026.06 | 88.89 | 95.06 | 16.037 | 13.284 | 2.2469 | |
| DynaHMRCBackbone=GPT-4o2026.06 | 80.59 | 90.76 | 18.5701 | 15.6532 | 4.1887 | |
| COELA2026.06 | 77.78 | 83.33 | 18.67 | 16.41 | 2.49 | |
| DynaHMRCBackbone=Qwen2-7B2026.06 | 66.67 | 69.14 | 18.7037 | 13.3827 | 2.2346 | |
| MCTST=52026.06 | 40.74 | 48.15 | 25.5185 | — | — | |
| MCTS2026.06 | 37.04 | 40.12 | 24.4444 | — | — |