Research
Benchmarks for “question answering”
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
9,723 benchmarksPage 192 of 389
Search results
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Quantitative Spatial Visual Question Answering | QSpatial-Bench | 10 | Mar 27, 2026 | ||
| Multiple Choice Question Answering | Long-form Multiple Choice Question Answering benchmark | 10 | Mar 27, 2026 | ||
| Question Answering | TriviaQA | 10 | Mar 25, 2026 | ||
| Question Answering | MuSiQue | 10 | Mar 25, 2026 | ||
| Embodied Question Answering | OpenEQA EM-EQA Episodes up to 32 frames | 10 | Mar 25, 2026 | ||
| Question Answering | HiTab | 10 | Mar 18, 2026 | ||
| Question Answering | TAT | 10 | Mar 18, 2026 | ||
| Question Answering | FeTaQA | 10 | Mar 18, 2026 | ||
| Long Video Question Answering | VideoMME long 30–60 min | 10 | Mar 17, 2026 | ||
| Visual Question Answering | MSVQA Indoor T=5 (test) | 10 | Mar 16, 2026 | ||
| Visual Question Answering | MSVQA Low altitude T=5 (test) | 10 | Mar 16, 2026 | ||
| Visual Question Answering | MSVQA Underwater T=5 (test) | 10 | Mar 16, 2026 | ||
| Visual Question Answering | MSVQA High altitude T=5 (test) | 10 | Mar 16, 2026 | ||
| standard QA | SQuAD v2 | 10 | Mar 16, 2026 | ||
| Visual Question Answering | XLRS-Bench vqa | 10 | Mar 13, 2026 | ||
| Visual Question Answering | VRSBench vqa | 10 | Mar 13, 2026 | ||
| Visual Question Answering | 3DRad 1.0 (test) | 10 | Mar 13, 2026 | ||
| Visual Question Answering | M3D 1.0 (test) | 10 | Mar 13, 2026 | ||
| Long-text Question Answering | UltraDomain | 10 | Mar 13, 2026 | ||
| Visual Question Answering | ScienceQA (val) | 10 | May 26, 2026 | ||
| Multi-audio Multiple-choice Question Answering | MUGEN | 10 | Mar 11, 2026 | ||
| Medical Question Answering | MMLU | 10 | Mar 11, 2026 | ||
| Medical Question Answering | MedQA | 10 | Mar 11, 2026 | ||
| Medical Question Answering | PubMedQA | 10 | Mar 11, 2026 | ||
| Medical Question Answering | MedQA USMLE | 10 | Mar 11, 2026 |