Planning on HM3D
78.4SPLSERP
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SERPBackbone=Qwen3-Max, Scenario=008292026.03 | 78.4 | 95.6 | — | |
| SERPBackbone=GPT-4o, Scenario=008292026.03 | 75.1 | 84.4 | — | |
| SERPBackbone=Qwen3-Max, Scenario=008242026.03 | 72.9 | 91.1 | — | |
| SERPBackbone=Qwen3-Max, Scenario=008772026.03 | 72.9 | 88.9 | — | |
| SERPBackbone=Qwen3-Max, Scenario=008432026.03 | 71.1 | 88.9 | — | |
| SERPBackbone=GPT-4o, Scenario=008772026.03 | 70.4 | 80 | — | |
| SERPBackbone=Qwen3-Max, Scenario=008732026.03 | 70.2 | 86.7 | — | |
| SERPBackbone=GPT-4o, Scenario=008242026.03 | 66.9 | 77.8 | — | |
| SERPBackbone=Qwen3-Max, Scenario=008612026.03 | 64.9 | 82.2 | — | |
| SERPBackbone=GPT-4o, Scenario=008432026.03 | 64.8 | 80 | — | |
| SERPBackbone=GPT-4o, Scenario=008732026.03 | 59 | 71.1 | — | |
| SERPBackbone=GPT-4o, Scenario=008612026.03 | 53.4 | 66.7 | — | |
| SayPlanBackbone=Qwen3-Max, Scenario=008732026.03 | 49.3 | 82.2 | — | |
| SayPlanBackbone=Qwen3-Max, Scenario=008772026.03 | 47.4 | 66.7 | — | |
| SayPlanBackbone=Qwen3-Max, Scenario=008432026.03 | 43.4 | 71.1 | — | |
| SayPlanBackbone=Qwen3-Max, Scenario=008242026.03 | 41.3 | 68.9 | — | |
| SayPlanBackbone=Qwen3-Max, Scenario=008292026.03 | 40.2 | 60 | — | |
| SayPlanBackbone=Qwen3-Max, Scenario=008612026.03 | 38.1 | 77.8 | — | |
| SayPlanBackbone=Qwen3-Max, Scenario=Avg.2026.03 | — | — | 53.2 | |
| SERPBackbone=GPT-4o, Scenario=Avg.2026.03 | — | — | 93.9 | |
| SERPBackbone=Qwen3-Max, Scenario=Avg.2026.03 | — | — | 90.9 |