Research
Benchmarks for “question answering”
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
9,723 benchmarksPage 112 of 389
Search results
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Video Question Answering | Video-MME w.o. sub. Medium | 16 | Jul 3, 2026 | ||
| Video Question Answering | Video-MME w.o. sub. Short | 16 | Jul 3, 2026 | ||
| Visual Question Answering | Average over [20-22, 50] | 16 | Jul 2, 2026 | ||
| Long-context Question Answering | LoCoMo (test) | 16 | Jul 2, 2026 | ||
| Question Answering | HotpotQA | 16 | Jul 2, 2026 | ||
| Question Answering | MS-MARCO | 16 | Jul 2, 2026 | ||
| Question Answering | NQ | 16 | Jul 2, 2026 | ||
| Medical Visual Question Answering | MIMIC-Ext MIMIC-CXR VQA | 16 | Jul 1, 2026 | ||
| Medical Visual Question Answering | Quilt-VQA | 16 | Jul 1, 2026 | ||
| Medical Visual Question Answering | VQA-Med 2021 | 16 | Jul 1, 2026 | ||
| Medical Visual Question Answering | Medical VQA | 16 | Jul 1, 2026 | ||
| Visual Question Answering | VQA v2 | 16 | Jul 7, 2026 | ||
| Video Question Answering | EgoSchema Sub. | 16 | Jun 30, 2026 | ||
| Question Answering | CONFLICTS | 16 | Jun 25, 2026 | ||
| Video Question Answering | ViTexQA | 16 | Jun 24, 2026 | ||
| Knowledge Question Answering | HLE | 16 | Jun 23, 2026 | ||
| Medical Visual Question Answering | slake | 16 | Jun 19, 2026 | ||
| Medical Visual Question Answering | vqa-rad | 16 | Jun 19, 2026 | ||
| Medical Visual Question Answering | med-vqa | 16 | Jun 19, 2026 | ||
| Multi-turn Code-Switched Question Answering | PingPong answerable QA (Indonesian–English id-en) (test) | 16 | Jun 19, 2026 | ||
| Subjective Search Question Answering | Internal Evaluation Subjective Q&A | 16 | Jun 19, 2026 | ||
| Multi-Hop Question Answering | MuSiQue | 16 | Jun 17, 2026 | ||
| Factual Question Answering | PopQA | 16 | Jun 17, 2026 | ||
| Multi-hop Question Answering | MuSiQue | 16 | Jun 12, 2026 | ||
| Multi-hop Question Answering | 2WikiMultiHopQA | 16 | Jun 12, 2026 |