Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1694 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Spatial Reasoning | VSI-Bench tiny | 19 | Jun 9, 2026 | ||
| Forecasting | Favorita | 19 | Jun 16, 2026 | ||
| Closed-loop Autonomous Driving | Bench2Drive v1 (test) | 19 | Jun 9, 2026 | ||
| Paper-Author Check | KDD Cup | 19 | Jun 9, 2026 | ||
| Paper-Author Check | WhoIsWho | 19 | Jun 9, 2026 | ||
| Video Question Answering | DailyOmni | 19 | Jun 9, 2026 | ||
| Behavioral Alignment Steering | Six Behavioral Traits (Persona Dataset) (test) | 19 | Jun 9, 2026 | ||
| Instructional Temporal Answer Grounding in Video | MedVidQA (test) | 19 | Jun 9, 2026 | ||
| Feature Reconstruction | Adult 10k rows QIdemo RankSwap release 1.0 (test) | 19 | Jun 9, 2026 | ||
| Image Classification | TinyImageNet | 19 | Jun 15, 2026 | ||
| Regression | six regression data sets | 19 | Jun 9, 2026 | ||
| Image Aesthetics Assessment | SPAQ (test) | 19 | Jun 9, 2026 | ||
| Image Aesthetics Assessment | ICAA17K (test) | 19 | Jun 9, 2026 | ||
| Pathology Visual Question Answering | PathMMU (test-all) | 19 | Jun 9, 2026 | ||
| Pathology Visual Question Answering | PathMMU tiny (test) | 19 | Jun 9, 2026 | ||
| Event-based Single Object Tracking | VisEvent | 19 | Jun 9, 2026 | ||
| Mathematical Reasoning | Math-500 | 19 | Jun 9, 2026 | ||
| Audio-to-Text Retrieval | FMACaps Eval | 19 | Jun 8, 2026 | ||
| Text-to-Audio Retrieval | FMACaps Eval | 19 | Jun 8, 2026 | ||
| Visual Planning | Behaviour Mini | 19 | Jun 5, 2026 | ||
| Visual Planning | Maze | 19 | Jun 5, 2026 | ||
| Visual Planning | FrozenLake | 19 | Jun 5, 2026 | ||
| Value Diversity Evaluation | World Values Survey (WVS) BRA, CHN, MEX, NGA, NZL Wave 7 | 19 | Jun 5, 2026 | ||
| Commonsense QA | HellaSwag | 19 | Jun 18, 2026 | ||
| Time-series Reasoning | TSRBench | 19 | Jun 5, 2026 |