Question Answering on TruthfulQA (Performance Score)
81.1Performance ScoreDeepSeek-R1 w/ GuarantRAG
Evaluation Results
| Method | Links | |
|---|---|---|
| DeepSeek-R1 w/ GuarantRAGBackbone=DeepSeek-R1, RAG Strategy=GuarantRAG, Retriever=BM252026.04 | 81.1 | |
| DeepSeek-R1 w/ P-RAGBackbone=DeepSeek-R1, RAG Strategy=P-RAG, Retriever=BM252026.04 | 79.4 | |
| DeepSeek-V3 w/ GuarantRAGBackbone=DeepSeek-V3, RAG Strategy=GuarantRAG, Retriever=BM252026.04 | 79.3 | |
| Gemini-2.5-Pro w/ GuarantRAGBackbone=Gemini-2.5-Pro, RAG Strategy=GuarantRAG, Retriever=BM252026.04 | 78.7 | |
| DeepSeek-V3 w/ P-RAGBackbone=DeepSeek-V3, RAG Strategy=P-RAG, Retriever=BM252026.04 | 77.9 | |
| DeepSeek-R1 w/ SelfRAGBackbone=DeepSeek-R1, RAG Strategy=SelfRAG, Retriever=BM252026.04 | 77.8 | |
| Claude-3.7-Sonnet w/ GuarantRAGBackbone=Claude-3.7-Sonnet, RAG Strategy=GuarantRAG, Retriever=BM252026.04 | 77.4 | |
| Gemini-2.5-Pro w/ P-RAGBackbone=Gemini-2.5-Pro, RAG Strategy=P-RAG, Retriever=BM252026.04 | 77.1 | |
| DeepSeek-V3 w/ SelfRAGBackbone=DeepSeek-V3, RAG Strategy=SelfRAG, Retriever=BM252026.04 | 76.2 | |
| DeepSeek-R1 w/ Standard RAGBackbone=DeepSeek-R1, RAG Strategy=Standard RAG, Retriever=BM252026.04 | 76.1 | |
| Claude-3.7-Sonnet w/ P-RAGBackbone=Claude-3.7-Sonnet, RAG Strategy=P-RAG, Retriever=BM252026.04 | 75.8 | |
| Gemini-2.5-Pro w/ SelfRAGBackbone=Gemini-2.5-Pro, RAG Strategy=SelfRAG, Retriever=BM252026.04 | 75.4 | |
| DeepSeek-V3 w/ Standard RAGBackbone=DeepSeek-V3, RAG Strategy=Standard RAG, Retriever=BM252026.04 | 74.6 | |
| GuarantRAGBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 74.1 | |
| Claude-3.7-Sonnet w/ SelfRAGBackbone=Claude-3.7-Sonnet, RAG Strategy=SelfRAG, Retriever=BM252026.04 | 74 | |
| DeepSeek-R1Backbone=DeepSeek-R1, RAG Strategy=Base, Retriever=BM252026.04 | 73.8 | |
| Gemini-2.5-Pro w/ Standard RAGBackbone=Gemini-2.5-Pro, RAG Strategy=Standard RAG, Retriever=BM252026.04 | 73.7 | |
| o12026.04 | 73.1 | |
| GuarantRAGBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 72.4 | |
| Claude-3.7-Sonnet w/ Standard RAGBackbone=Claude-3.7-Sonnet, RAG Strategy=Standard RAG, Retriever=BM252026.04 | 72.3 | |
| DeepSeek-V3Backbone=DeepSeek-V3, RAG Strategy=Base, Retriever=BM252026.04 | 72.1 | |
| GPT-4o2026.04 | 71.8 | |
| P-RAGBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 71.6 | |
| Gemini-2.5-ProBackbone=Gemini-2.5-Pro, RAG Strategy=Base, Retriever=BM252026.04 | 71.3 | |
| GuarantRAGBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 69.8 | |
| Claude-3.7-SonnetBackbone=Claude-3.7-Sonnet, RAG Strategy=Base, Retriever=BM252026.04 | 69.8 | |
| SOLARBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 69.7 | |
| DRAGINBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 69.3 | |
| P-RAGBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 68.9 | |
| FLAREBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 68.9 | |
| RQ-RAGBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 68.2 | |
| SOLARBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 67.1 | |
| DRAGINBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 66.7 | |
| SelfRAGBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 66.5 | |
| FLAREBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 66.3 | |
| RQ-RAGBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 65.8 | |
| DA-RAGBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 65.8 | |
| P-RAGBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 65.4 | |
| SOLARBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 64.2 | |
| SelfRAGBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 64.2 | |
| DRAGINBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 63.9 | |
| FLAREBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 63.5 | |
| DA-RAGBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 63.5 | |
| RQ-RAGBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 62.7 | |
| Standard RAGBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 62.1 | |
| SelfRAGBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 61.4 | |
| DA-RAGBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 60.8 | |
| Standard RAGBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 60.7 | |
| Standard RAGBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 58.1 | |
| Qwen3-14B-TBase Model=Qwen3-14B, Thinking Mode=true2026.04 | 57.8 | |
| Qwen3-14BBase Model=Qwen3-14B, Thinking Mode=false2026.04 | 54.9 | |
| Qwen3-8BBase Model=Qwen3-8B, Thinking Mode=false2026.04 | 52.3 |