Question Answering on TQA
92.3AccuracyRankRAG-70B
Evaluation Results
| Method | Links | |
|---|---|---|
| RankRAG-70BRetrieval=Yes2026.03 | 92.3 | |
| RankRAG-8BRetrieval=Yes2026.03 | 89.5 | |
| Llama3.1-70B+Hit-RAGFramework=Hit-RAG2026.03 | 84.6 | |
| ETTCAggregation Strategy=ETTC, Model Scale=7B-12B Ensemble2026.05 | 83.9 | |
| Llama3.1-70B+R-InsRetrieval=Yes2026.03 | 83.8 | |
| VotingAggregation Strategy=Majority Voting, Model Scale=7B-12B Ensemble2026.05 | 83.65 | |
| Qwen3-32B+Hit-RAGFramework=Hit-RAG2026.03 | 81.7 | |
| Llama3.1-8B+R-InsRetrieval=Yes2026.03 | 80 | |
| Qwen3-8B+Hit-RAGFramework=Hit-RAG2026.03 | 78.9 | |
| Gemma-12BModel Backbone=Gemma, Model Scale=12B, Aggregation Strategy=Single Model2026.05 | 78.86 | |
| Qwen-7BModel Backbone=Qwen, Model Scale=7B, Aggregation Strategy=Single Model2026.05 | 78.5 | |
| Sonnet-3.5Retrieval=None2026.03 | 78.4 | |
| Pixtral-12BModel Backbone=Pixtral, Model Scale=12B, Aggregation Strategy=Single Model2026.05 | 77.34 | |
| Qwen3-4B+Hit-RAGFramework=Hit-RAG2026.03 | 74.4 | |
| ChatGPTRetrieval=None2026.03 | 74.3 | |
| Speculative RAG-7BRetrieval=Yes2026.03 | 74.2 | |
| Llama3.1-8B+Hit-RAGFramework=Hit-RAG2026.03 | 74 | |
| LogicGazeBackbone=LLaMA3-8B, Retrieval Setting=Yes, Evaluation Protocol=RAG2026.01 | 73.8 | |
| RAS-8BRetrieval=Yes2026.03 | 73.8 | |
| RAS-7BRetrieval=Yes2026.03 | 72.7 | |
| IterDRAGBackbone=LLaMA3-8B, Retrieval Setting=Yes, Evaluation Protocol=RAG2026.01 | 71.9 | |
| RankRAGBackbone=LLaMA3-8B, Retrieval Setting=Yes, Evaluation Protocol=RAG2026.01 | 71.7 | |
| LogicGazeBackbone=Qwen2.5-7B, Retrieval Status=With Retrieval, Evaluation Protocol=RAG2026.01 | 71.5 | |
| LLaMA-11BModel Backbone=LLaMA, Model Scale=11B, Aggregation Strategy=Single Model2026.05 | 70.41 | |
| AutoRAGBackbone=LLaMA3-8B, Retrieval Setting=Yes, Evaluation Protocol=RAG2026.01 | 70.4 | |
| RankRAGBackbone=Qwen2.5-7B, Retrieval Status=With Retrieval, Evaluation Protocol=RAG2026.01 | 70.2 | |
| IterDRAGBackbone=Qwen2.5-7B, Retrieval Status=With Retrieval, Evaluation Protocol=RAG2026.01 | 69.9 | |
| Self-RAG-13BRetrieval=Yes2026.03 | 69.3 | |
| RQ-RAGBackbone=LLaMA3-8B, Retrieval Setting=Yes, Evaluation Protocol=RAG2026.01 | 68.6 | |
| AutoRAGBackbone=Qwen2.5-7B, Retrieval Status=With Retrieval, Evaluation Protocol=RAG2026.01 | 68.5 | |
| Llama3.1-70BRetrieval=None2026.03 | 68.5 | |
| RQ-RAGBackbone=Qwen2.5-7B, Retrieval Status=With Retrieval, Evaluation Protocol=RAG2026.01 | 67.4 | |
| Alpaca-13BRetrieval=Yes2026.03 | 66.9 | |
| Self-RAGBackbone=LLaMA3-8B, Retrieval Setting=Yes, Evaluation Protocol=RAG2026.01 | 66.5 | |
| Self-RAG-7BRetrieval=Yes2026.03 | 66.4 | |
| Qwen3-32BRetrieval=None2026.03 | 65.9 | |
| Ret-ChatGPTRetrieval=None2026.03 | 65.7 | |
| Self-RAGBackbone=Qwen2.5-7B, Retrieval Status=With Retrieval, Evaluation Protocol=RAG2026.01 | 65.6 | |
| SFT+RetBackbone=Qwen2.5-7B, Retrieval Status=With Retrieval, Evaluation Protocol=SFT2026.01 | 61.3 | |
| Alpaca-13BRetrieval=None2026.03 | 61.3 | |
| GPT-4o-miniBackbone=GPT-4o-mini, Retrieval Status=With Retrieval2026.01 | 60.1 | |
| SFTBackbone=Qwen2.5-7B, Retrieval Status=Without Retrieval, Evaluation Protocol=SFT2026.01 | 59.2 | |
| Llama3.1-8BRetrieval=None2026.03 | 58.4 | |
| SAIL-7BBackbone=Qwen2.5-7B, Retrieval Status=With Retrieval, Evaluation Protocol=RAG2026.01 | 57.5 | |
| SFT+RetBackbone=LLaMA3-8B, Retrieval Setting=Yes, Evaluation Protocol=SFT2026.01 | 57.4 | |
| Qwen3-8BRetrieval=None2026.03 | 57.3 | |
| GPT-4oBackbone=GPT-4o, Retrieval Status=With Retrieval2026.01 | 56.2 | |
| SFTBackbone=LLaMA3-8B, Retrieval Setting=No, Evaluation Protocol=SFT2026.01 | 55 | |
| SPAR-KBackbone=Step-Audio-2, Text EE=-, Speech EE=Triple (22)2026.03 | 51 | |
| Qwen3-4BRetrieval=None2026.03 | 50.1 | |
| SPAR-KBackbone=Step-Audio-2, Text EE=-, Speech EE=Even (22)2026.03 | 49.2 | |
| Step-Audio-2Backbone=Step-Audio-2, Text EE=-, Speech EE=-2026.03 | 49.1 | |
| SPAR-KBackbone=Step-Audio-2, Text EE=-, Speech EE=Odd (22)2026.03 | 48.7 | |
| Zero-Shot-Instruct+RetBackbone=LLaMA3-8B, Retrieval Setting=Yes, Evaluation Protocol=Zero-Shot-Instruct2026.01 | 48.3 | |
| Step-Audio-2Backbone=Step-Audio-2, Text EE=-, Speech EE=Fixed (25)2026.03 | 46.7 | |
| Zero-Shot-InstructBackbone=LLaMA3-8B, Retrieval Setting=No, Evaluation Protocol=Zero-Shot-Instruct2026.01 | 46.3 | |
| Zero-Shot-Chat+RetBackbone=Qwen2.5-7B, Retrieval Status=With Retrieval, Evaluation Protocol=Chat2026.01 | 45.9 | |
| SAIL-7BBackbone=SAIL-7B, Retrieval Setting=Yes, Evaluation Protocol=RAG2026.01 | 45.9 | |
| GLM-4-VoiceBackbone=GLM-4-Voice, Text EE=-, Speech EE=Conf (36)2026.03 | 45.7 | |
| Zero-Shot-ChatBackbone=Qwen2.5-7B, Retrieval Status=Without Retrieval, Evaluation Protocol=Chat2026.01 | 45.5 | |
| GLM-4-VoiceBackbone=GLM-4-Voice, Text EE=-, Speech EE=Fixed (38)2026.03 | 45 | |
| GLM-4-VoiceBackbone=GLM-4-Voice, Text EE=-, Speech EE=-2026.03 | 44.9 | |
| SPAR-KBackbone=GLM-4-Voice, Text EE=-, Speech EE=Triple (37)2026.03 | 44.7 | |
| SPAR-KBackbone=GLM-4-Voice, Text EE=-, Speech EE=Odd (36)2026.03 | 43 | |
| Zero-Shot+RetBackbone=Qwen2.5-7B, Retrieval Status=With Retrieval, Evaluation Protocol=Zero-Shot2026.01 | 42.7 | |
| Zero-Shot+RetBackbone=LLaMA3-8B, Retrieval Setting=Yes, Evaluation Protocol=Zero-Shot2026.01 | 42.6 | |
| SPAR-KBackbone=GLM-4-Voice, Text EE=-, Speech EE=Even (36)2026.03 | 42 | |
| SPAR-KBackbone=GLM-4-Voice, Text EE=-, Speech EE=Even (33)2026.03 | 41.8 | |
| SPAR-KBackbone=GLM-4-Voice, Text EE=-, Speech EE=Even (35)2026.03 | 41.2 | |
| Zero-ShotBackbone=Qwen2.5-7B, Retrieval Status=Without Retrieval, Evaluation Protocol=Zero-Shot2026.01 | 41 | |
| SPAR-KBackbone=GLM-4-Voice, Text EE=Conf (36), Speech EE=Even(36)2026.03 | 38.5 | |
| RoPE++EHModel Scale=1.5B, Context Length Setting=Short2025.12 | 37.1 | |
| RoPE++ECModel Scale=1.5B, Context Length Setting=Long2025.12 | 36.6 | |
| RoPEModel Scale=1.5B, Context Length Setting=Short2025.12 | 36.4 | |
| RoPEModel Scale=1.5B, Context Length Setting=Long2025.12 | 36.3 | |
| RoPE++EHModel Scale=1.5B, Context Length Setting=Long2025.12 | 36.1 | |
| RoPE++ECModel Scale=1.5B, Context Length Setting=Short2025.12 | 35.1 | |
| Zero-ShotBackbone=LLaMA3-8B, Retrieval Setting=No, Evaluation Protocol=Zero-Shot2026.01 | 30.2 | |
| Step-Audio-2Backbone=Step-Audio-2, Text EE=-, Speech EE=Conf (26)2026.03 | 28.5 | |
| SPAR-KBackbone=GLM-4-Voice, Text EE=Even (36), Speech EE=-2026.03 | 0 |