| SQuAD 1.1 (test) | ProphetNet | BLEU-425.8 | | 29 | 4mo ago |
| EduMath-CQ | EQPR | Win Rate47.11 | | 25 | 4mo ago |
| SQuAD (test) | partial copy + QA-based reranking | BLEU-144.61 | | 22 | 4mo ago |
| SQuAD | | BLEU-40.496 | | 21 | 4mo ago |
| SQuAD 1.1 | ERNIE-GEN_LARGE | METEOR0.2631 | | 21 | 4mo ago |
| Fairytale QA | | ROUGE-L54.8 | | 17 | 4mo ago |
| SQuAD 1.1 (dev) | ERNIE-GENLARGE | BLEU-425.4 | | 16 | 4mo ago |
| QT | NeoDiff | BLEU20.44 | | 14 | 4mo ago |
| Question Generation | MANTA-LM | BLEU0.186 | | 13 | 2mo ago |
| Computer Science | GLM-4-9B | Unique Questions99.5 | | 12 | 1mo ago |
| MSCOCO-VQA (test) | Humans2016 | METEOR60.8 | | 12 | 4mo ago |
| QSGen-ChildQ (test) | HIBRIDS-ENC | ROUGE-127.33 | | 11 | 4mo ago |
| SQuAD Du | UniLM-v2 | BLEU-424.43 | | 10 | 4mo ago |
| Question Generation | FlowLM | BLEU0.1634 | | 9 | 2mo ago |
| CoQA (val) | SG-CQG | Distinct-168.35 | | 9 | 4mo ago |
| SQuAD 1.1 (reversed dev-test) | ERNIE-GENLARGE | BLEU-426.95 | | 9 | 4mo ago |
| SQuAD | Semi-offline RL | BLEU-427.79 | | 8 | 1mo ago |
| QG | Meta-DiffuB | BLEU22.71 | | 8 | 4mo ago |
| Molweni (test) | Ins | BLEU Score20.26 | | 8 | 4mo ago |
| OR-ShARC (test) | EFT | F1 (BLEU-1)59.3 | | 7 | 4mo ago |
| OR-ShARC (dev) | EFT | F1 (BLEU-1)65.5 | | 7 | 4mo ago |
| SQuAD (Zhao split) | Our model | BLEU-426.3 | | 7 | 4mo ago |
| K-12 Math | GLM-4-9B | Unique97.71 | | 6 | 1mo ago |
| MusiQue 2hop | DPKG | B429.03 | | 6 | 4mo ago |
| FairytaleQA (test) | SkillQG | Q-B40.656 | | 6 | 4mo ago |