Metric: F1 (higher is better)
| # | Model↕ | F1▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | somebody | 27.13 | No | - | - | - |
| 2 | arxiv.org/abs/2103.06332 | 22.88 | No | Hurdles to Progress in Long-form Question Answer... | 2021-03-10 | Code |
| 3 | Training Set Retrieval (top 1) | 21.62 | No | - | - | - |
| 4 | BART | 19.23 | No | - | - | - |
| 5 | BART + DPR | 17.88 | No | - | - | - |
| 6 | Random Training Set Answer | 17.07 | No | - | - | - |
| 7 | multi-task small | 16.4 | No | - | - | - |
| 8 | T5-base | 16.1 | No | KILT: a Benchmark for Knowledge Intensive Langua... | 2020-09-04 | Code |
| 9 | Wikipedia | 15.91 | No | - | - | - |
| 10 | Sphere | 15.29 | No | - | - | - |
| 11 | Input Copying | 14.8 | No | - | - | - |
| 12 | RAG | 14.51 | No | KILT: a Benchmark for Knowledge Intensive Langua... | 2020-09-04 | Code |
| 13 | TABi | 0 | No | - | - | - |
| 14 | chriskuei | 0 | No | - | - | - |
| 15 | GENRE | 0 | No | - | - | - |
| 16 | Multi-task DPR | 0 | No | - | - | - |