Question Answering on SpiderQA (test)
5.494NACE (mean)LLM-only
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| LLM-onlyModel=GPT-4o-mini2026.02 | 5.494 | 0.6 | 45.94 | 0 | |
| LightRAGModel=GPT-4o-mini, Embedding Model=text-embedding-3-small2026.02 | 0.708 | 0.75 | 9.562 | 0.865 | |
| ReActModel=GPT-4o-mini, Embedding Model=text-embedding-3-small, max_iteration=102026.02 | 0.672 | 0.125 | 9.529 | 0.614 | |
| Naive RAGModel=GPT-4o-mini, Embedding Model=text-embedding-3-small2026.02 | 0.666 | 0.8 | 9.895 | 0.181 | |
| Multi-AgentModel=GPT-4o-mini2026.02 | 0.632 | 0.222 | 7.761 | 0.856 | |
| HippoRAGModel=GPT-4o-mini, Embedding Model=text-embedding-3-small2026.02 | 0.454 | 0.2 | 6.522 | 0.827 | |
| Single AgentModel=GPT-4o-mini2026.02 | 0.429 | 0.235 | 6.547 | 0.868 | |
| DeepNoteModel=GPT-4o-mini, Embedding Model=text-embedding-3-small2026.02 | 0.425 | 0.162 | 6.495 | 0.827 | |
| RATModel=GPT-4o-mini, Embedding Model=text-embedding-3-small2026.02 | 0.385 | 0.25 | 7.15 | 0.736 | |
| smolagentsModel=GPT-4o-mini2026.02 | 0.355 | 0.1 | 6.587 | 0.806 | |
| DFAModel=GPT-4o-mini2026.02 | 0.262 | 0.143 | 4 | 0.891 |