Question Answering on RD exam Single
85.8Overall AccuracyCogRAG+
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| CogRAG+Model=Qwen3-8B2026.04 | 85.8 | 87.3 | 90.7 | 84.6 | 84.7 | 84.1 | 92.3 | |
| CogRAGModel=Qwen3-8B2026.04 | 79.5 | 80.3 | 81.4 | 77.8 | 76.5 | 81 | 84.6 | |
| DenseModel=Qwen3-8B2026.04 | 78.2 | 77.8 | 80.6 | 77.1 | 74.5 | 79.8 | 76.9 | |
| BaselineModel=Qwen3-8B2026.04 | 73.4 | 72 | 72.7 | 73.5 | 65.3 | 77 | 71.8 | |
| BM25Model=Qwen3-8B2026.04 | 72.1 | 71 | 69.8 | 72.7 | 66.3 | 74.6 | 71.8 | |
| HybridModel=Qwen3-8B2026.04 | 71.9 | 70 | 69.8 | 73.4 | 62.2 | 75.4 | 69.2 | |
| CogRAG+Model=Llama3.1-8B2026.04 | 60.3 | 62.7 | 68.2 | 60.1 | 61.2 | 54.8 | 69.2 | |
| CogRAGModel=Llama3.1-8B2026.04 | 59.2 | 60.8 | 60.5 | 61.4 | 54.1 | 56 | 71.8 | |
| DenseModel=Llama3.1-8B2026.04 | 58.1 | 58.4 | 59.7 | 61.4 | 59.2 | 52.8 | 59 | |
| HybridModel=Llama3.1-8B2026.04 | 56.4 | 57.4 | 57.4 | 57.7 | 57.1 | 53.2 | 61.5 | |
| BaselineModel=Llama3.1-8B2026.04 | 49.3 | 49.3 | 40.6 | 53.1 | 46.9 | 49.2 | 56.4 | |
| BM25Model=Llama3.1-8B2026.04 | 47.7 | 48.4 | 48.8 | 46.8 | 51 | 46.8 | 48.7 |