Research
Benchmarks for “question answering”
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
9,723 benchmarksPage 289 of 389
Search results
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-hop Knowledge-based Question Answering | PathQuestion M 1.0 | 6 | Feb 26, 2026 | ||
| Multiple Choice Question Answering | MMLU (Hendrycks Tasks) Part 2 | 6 | Feb 26, 2026 | ||
| Open-domain Question Answering | ComplexWebQuestions (CWQ) (dev) | 6 | Feb 26, 2026 | ||
| Question Answering | PubMedQA | 6 | Feb 26, 2026 | ||
| Question Answering | ELI5 | 6 | Feb 26, 2026 | ||
| Video Question Answering | AVSD-QA (test) | 6 | Feb 26, 2026 | ||
| Extractive Question Answering | SQuAD MRQA | 6 | Feb 26, 2026 | ||
| Multiple-choice Question Answering | Ego4D (first-view) | 6 | Feb 26, 2026 | ||
| Conversational Question Answering | CoQA without human rewrites v1.0 (test) | 6 | Feb 26, 2026 | ||
| Question Answering | X-CSQA | 6 | Feb 26, 2026 | ||
| Question Answering | TAT-QA 1.0 (test) | 6 | Feb 26, 2026 | ||
| Question Answering | HybridQA 1.0 (test) | 6 | Feb 26, 2026 | ||
| Question Answering | HybridQA 1.0 (dev) | 6 | Feb 26, 2026 | ||
| Question Answering | BoolQ (dev) | 6 | Feb 27, 2026 | ||
| Question Answering | BoolQ CS | 6 | Feb 26, 2026 | ||
| Question Answering | NP-BoolQ | 6 | Feb 26, 2026 | ||
| Question Answering | DROP CS | 6 | Feb 26, 2026 | ||
| Question Answering | ROPES CS | 6 | Feb 26, 2026 | ||
| Question Answering | ROPES | 6 | Feb 26, 2026 | ||
| Question Answering | Quoref CS | 6 | Feb 26, 2026 | ||
| Question Answering | Quoref | 6 | Feb 26, 2026 | ||
| Question Answering | NewsQA | 6 | Feb 26, 2026 | ||
| Cloze-style Question Answering | ReCoRD (dev) | 6 | Feb 26, 2026 | ||
| Retrieval Question Answering | Text | 6 | Feb 26, 2026 | ||
| Retrieval Question Answering | RE | 6 | Feb 26, 2026 |