Multi-hop Question Answering on HotpotQA (Performance Score)
78.2Performance ScoreGuarantRAG
Evaluation Results
| Method | Links | |
|---|---|---|
| GuarantRAGBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 78.2 | |
| P-RAGBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 74.9 | |
| SOLARBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 72.5 | |
| o12026.04 | 72.3 | |
| DRAGINBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 72.1 | |
| FLAREBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 71.7 | |
| GuarantRAGBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 71.6 | |
| GPT-4o2026.04 | 70.9 | |
| RQ-RAGBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 70.8 | |
| SelfRAGBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 69.1 | |
| GuarantRAGBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 68.9 | |
| P-RAGBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 68.1 | |
| DA-RAGBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 67.3 | |
| SOLARBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 66 | |
| DRAGINBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 65.6 | |
| FLAREBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 65.1 | |
| P-RAGBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 64.7 | |
| RQ-RAGBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 64.3 | |
| Standard RAGBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 63.4 | |
| SOLARBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 63.1 | |
| DRAGINBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 62.8 | |
| SelfRAGBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 62.5 | |
| FLAREBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 62.4 | |
| RQ-RAGBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 61.5 | |
| DA-RAGBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 60.8 | |
| SelfRAGBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 59.2 | |
| Qwen3-14B-TBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 58.7 | |
| DA-RAGBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 57.9 | |
| Standard RAGBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 57.2 | |
| Standard RAGBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 54.3 | |
| Qwen3-14BBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 51.3 | |
| Qwen3-8BBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 48.7 |