Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 485 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Depth Completion | IBims-1 | 43 | May 13, 2026 | ||
| Reasoning Video Object Segmentation | ReasonVOS | 43 | May 15, 2026 | ||
| Target Speech Extraction | Relative Cue-based TSE Mixtures (test) | 43 | Mar 4, 2026 | ||
| Code generation | HumanEval | 43 | Jun 11, 2026 | ||
| Multi-turn conversation | MT-bench | 43 | Mar 4, 2026 | ||
| Knowledge-Intensive Reasoning | MuSiQue | 43 | Jun 2, 2026 | ||
| Category-level 6D Object Pose Estimation | REAL275 | 43 | Jun 23, 2026 | ||
| Procedure Planning | CrossTask | 43 | Mar 5, 2026 | ||
| Text Classification | AGNews | 43 | Mar 5, 2026 | ||
| Instruction Following | Super-Natural Instructions | 43 | Mar 5, 2026 | ||
| Image Understanding | TextVQA | 43 | May 26, 2026 | ||
| Zero-shot Prediction | HellaSwag | 43 | May 26, 2026 | ||
| Classical Image Super-Resolution | Manga109 | 43 | Mar 11, 2026 | ||
| Node Classification | Wisconsin (60%/20%/20%) | 43 | Mar 11, 2026 | ||
| Unconditional Molecular Generation | MOSES | 43 | Jun 11, 2026 | ||
| Software Engineering | SWE-bench Verified | 43 | Jul 9, 2026 | ||
| PDE solving | 1D Burgers | 43 | Jun 23, 2026 | ||
| Survival Analysis | TCGA-LUSC | 43 | Jun 11, 2026 | ||
| Image Quality Assessment | AGIQA | 43 | Apr 21, 2026 | ||
| Object Navigation | HM3D v1 (val) | 43 | Jun 11, 2026 | ||
| Trajectory Prediction | Waymo Open Motion Dataset (WOMD) (test) | 43 | May 26, 2026 | ||
| Medical Question Answering | DDXPlus | 43 | Mar 11, 2026 | ||
| OS GUI Agentic Task Execution | OSWorld 361 tasks (Verified) | 43 | Mar 18, 2026 | ||
| Question Answering | MultiExpertQA All Base and Fine-tuned (FT) | 43 | Feb 26, 2026 | ||
| Language Modeling | Wikipedia | 43 | May 28, 2026 |