Searching on HM3D
91SPLSERP
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SERPBackbone=Qwen3-Max, Scenario=008292026.03 | 91 | 97.8 | — | |
| SERPBackbone=Qwen3-Max, Scenario=008242026.03 | 87 | 95.6 | — | |
| SERPBackbone=GPT-4o, Scenario=008292026.03 | 86.5 | 91.1 | — | |
| SERPBackbone=Qwen3-Max, Scenario=008772026.03 | 85.1 | 95.6 | — | |
| SERPBackbone=Qwen3-Max, Scenario=008432026.03 | 84.1 | 95.6 | — | |
| SERPBackbone=Qwen3-Max, Scenario=008732026.03 | 83 | 93.3 | — | |
| SERPBackbone=GPT-4o, Scenario=008242026.03 | 81.5 | 86.7 | — | |
| SERPBackbone=GPT-4o, Scenario=008772026.03 | 78.5 | 84.4 | — | |
| SERPBackbone=GPT-4o, Scenario=008432026.03 | 76 | 84.4 | — | |
| SERPBackbone=Qwen3-Max, Scenario=008612026.03 | 75.6 | 88.9 | — | |
| SERPBackbone=GPT-4o, Scenario=008732026.03 | 72.8 | 80 | — | |
| SERPBackbone=GPT-4o, Scenario=008612026.03 | 65.8 | 75.6 | — | |
| SayPlanBackbone=Qwen3-Max, Scenario=008732026.03 | 59.8 | 86.7 | — | |
| SayPlanBackbone=Qwen3-Max, Scenario=008292026.03 | 57.2 | 73.3 | — | |
| SayPlanBackbone=Qwen3-Max, Scenario=008772026.03 | 56.9 | 71.1 | — | |
| SayPlanBackbone=Qwen3-Max, Scenario=008242026.03 | 56.1 | 75.6 | — | |
| SayPlanBackbone=Qwen3-Max, Scenario=008432026.03 | 56 | 77.8 | — | |
| SayPlanBackbone=Qwen3-Max, Scenario=008612026.03 | 53.2 | 84.4 | — | |
| SayPlanBackbone=Qwen3-Max, Scenario=Avg.2026.03 | — | — | 75.6 | |
| SERPBackbone=GPT-4o, Scenario=Avg.2026.03 | — | — | 97 | |
| SERPBackbone=Qwen3-Max, Scenario=Avg.2026.03 | — | — | 95.4 |