Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2472 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 3D Object Classification | ScanNet (test) | 15 | Feb 27, 2026 | ||
| Video Retrieval | Youcook2 | 15 | Apr 30, 2026 | ||
| Zero-Shot Recognition | AWA2 pure ZSL setting (target classes) | 15 | Feb 27, 2026 | ||
| Image Classification | AWA2 | 15 | Feb 27, 2026 | ||
| Detection | IRSTD-1k | 15 | Jun 23, 2026 | ||
| Open-World Object Detection | S-OWODB Task 4 | 15 | Apr 1, 2026 | ||
| Open-World Object Detection | S-OWODB Task 1 | 15 | Apr 1, 2026 | ||
| Open-World Object Detection | M-OWODB Task 4 | 15 | Apr 1, 2026 | ||
| Multiple Choice Question Answering | TruthfulQA MC | 15 | Feb 26, 2026 | ||
| Truthful Question Answering | TruthfulQA | 15 | Feb 26, 2026 | ||
| Question Answering | TriviaQA | 15 | Feb 26, 2026 | ||
| Reading Comprehension | SQuAD Extract | 15 | Feb 26, 2026 | ||
| Question Answering | SQuAD Abstract | 15 | Feb 26, 2026 | ||
| Multiple Choice Question Answering | SciQ MC | 15 | Feb 26, 2026 | ||
| Question Answering | SciQ Abstract | 15 | Feb 26, 2026 | ||
| Physical Commonsense Reasoning | PIQA | 15 | Feb 26, 2026 | ||
| Question Answering | OpenBookQA | 15 | Feb 26, 2026 | ||
| Multi-task Knowledge Understanding | MMLU | 15 | Feb 26, 2026 | ||
| Question Answering | HotpotQA | 15 | Feb 26, 2026 | ||
| Question Answering | BoolQA | 15 | Feb 26, 2026 | ||
| Question Answering | ARC Easy | 15 | Feb 26, 2026 | ||
| Question Answering | ARC Challenge | 15 | Feb 26, 2026 | ||
| Rewrite Selection | 16 QA Datasets Aggregate | 15 | Feb 26, 2026 | ||
| Bimanual Manipulation | RoboTwin Hard setting 2.0 (test) | 15 | May 12, 2026 | ||
| Multi-class Classification | Pageblocks | 15 | May 13, 2026 |