Question Answering on OpenBookQA Official Leaderboard
95.2AccuracyX-Reasoner
Evaluation Results
| Method | Links | |
|---|---|---|
| X-Reasoner2023.12 | 95.2 | |
| KnowGPT2023.12 | 92.6 | |
| GenMCensemble=true2023.12 | 92 | |
| Human Performance2023.12 | 91.7 | |
| GenMCensemble=false2023.12 | 89.8 | |
| DRAGON2023.12 | 87.8 | |
| GSC2023.12 | 87.4 | |
| UnifiedQA2023.12 | 87.2 | |
| JointLK2023.12 | 85.6 | |
| HamQA2023.12 | 85 | |
| GreaseLM2023.12 | 84.8 | |
| QA-GNN2023.12 | 82.8 | |
| MHGRN2023.12 | 80.6 | |
| w/o KGKnowledge Graph usage=None2023.12 | 77.8 |