| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Knowledge Graph Question Answering | CWQ | Hit@185.2 | 245 | |
| Knowledge Graph Question Answering | CWQ (test) | Hits@188.95 | 158 | |
| Multi-Hop Knowledge Graph Question Answering | CWQ | Hits@181.4 | 84 | |
| Knowledge Base Question Answering | CWQ (test) | F1 Score81.3 | 44 | |
| Knowledge Base Question Answering | CWQ Freebase (test) | Hits@186 | 38 | |
| Multi-hop Question Answering | CWQ | Pass@155.8 | 36 | |
| Knowledge Base Question Answering | CWQ | Hits@186.3 | 30 | |
| Question Answering | CWQ | Accuracy23.62 | 30 | |
| Question Answering | CWQ | Hits@185.2 | 27 | |
| Discriminative Evaluation | CWQ (test) | Binary Accuracy92.88 | 24 | |
| Knowledge Base Question Answering | CWQ | Answer F151.74 | 18 | |
| Knowledge Base Completion | CWQ 50% KB | MRR61.4 | 16 | |
| Knowledge Base Completion | CWQ (30% KB) | MRR58.8 | 16 | |
| Knowledge Graph Question Answering | CWQ Switzerland | Accuracy68 | 14 | |
| Entity Linking | CWQ (test) | Precision82.43 | 13 | |
| Knowledge Graph Question Answering | CWQ | # Calls1 | 12 | |
| Knowledge Base Question Answering | CWQ 50% KB | Hits@150.8 | 12 | |
| Knowledge Base Question Answering | CWQ 30% KB | Hits@150.2 | 12 | |
| Hallucination Detection | CWQ | F1 Score87.4 | 11 | |
| Hallucination Detection | CWQ | F1 Score87.4 | 11 | |
| Question Answering | CWQ | Exact Match (EM)25 | 10 | |
| Multi-hop Reasoning | CWQ | Hits@182.2 | 10 | |
| Incomplete Knowledge Graph Question Answering | CWQ 40% knowledge gap | EM39.33 | 7 | |
| Knowledge Graph Question Answering | CWQ multi-entity | F1 Score64.9 | 7 | |
| Knowledge Base Question Answering | CWQ (hidden test) | Accuracy67.1 | 7 |