GraphRAG-Bench
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Complex Reasoning | GraphRAG-Bench | Rel86.02 | 27 | |
| Long-form Question Answering | GraphRAG-Bench Med | LLM Accuracy93.1 | 20 | |
| Multi-hop Question Answering | GraphRAG-Bench | LLM Accuracy87.1 | 15 | |
| Question Answering | GraphRAG-Bench Medical 1,000 questions sample (val) | GPT Accuracy64.65 | 11 | |
| Creative Generation | GraphRAG-Bench Medical Dataset | Accuracy69.92 | 9 | |
| Contextual Summarization | GraphRAG-Bench Medical Dataset | Accuracy75.01 | 9 | |
| Complex Reasoning | GraphRAG-Bench Medical Dataset | Accuracy (ACC)75.03 | 9 | |
| Fact Retrieval | GraphRAG-Bench Medical | Accuracy68.49 | 9 | |
| Creative Generation | GraphRAG-Bench | ACC56.94 | 9 | |
| Contextual Summarization | GraphRAG-Bench | Accuracy75.04 | 9 | |
| Fact Retrieval | GraphRAG-Bench | ACC (Fact Retrieval)67.42 | 9 | |
| Creative Generation | GraphRAG-Bench Medical | Recall93.56 | 9 | |
| Contextual Summarization | GraphRAG-Bench Medical Dataset | Recall93.73 | 9 | |
| Fact Retrieval | GraphRAG-Bench Medical Dataset | Recall88.9 | 9 | |
| Creative Generation | GraphRAG-Bench | Recall (Rec)78.52 | 9 | |
| Contextual Summarization | GraphRAG-Bench | Recall94.04 | 9 | |
| Fact Retrieval | GraphRAG-Bench | Recall83.17 | 9 | |
| Retrieval-Augmented Generation | GraphRAG-Bench | ACC (All)68.7 | 3 | |
| Retrieval-augmented Question Answering | GraphRAG-Bench 5-novel 519 questions | Precision41.9 | 3 |
Showing 19 of 19 rows