Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1163 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Graph Alignment | Celegans | 24 | Jun 23, 2026 | ||
| Traffic Flow Prediction | PeMS03 (test) | 24 | Jun 23, 2026 | ||
| Mathematical Reasoning | MATH 500, GSM8K, AIME 24, AMC 23, OlympiadBench, and Minerva Math (test) | 24 | Jun 23, 2026 | ||
| In-hand reorientation | YCB 1.0 (test) | 24 | Jun 23, 2026 | ||
| Machine Translation | Real-world translation benchmarks Ja→En | 24 | Jun 23, 2026 | ||
| Constrained Diversity Optimisation | a280 (TSPlib) 1.0 (test) | 24 | Jun 23, 2026 | ||
| Constrained Diversity Optimisation | TSPlib eil101 1.0 (test) | 24 | Jun 23, 2026 | ||
| Constrained Diversity Optimisation | TSPlib st70 1.0 (test) | 24 | Jun 23, 2026 | ||
| Pose Estimation | Forest Environment (Simulation) Various difficulties (Easy, Medium, Hard) | 24 | Jun 23, 2026 | ||
| Web agent attack | SeeAct | 24 | Jun 23, 2026 | ||
| Visual Question Answering | CktBench | 24 | Jun 23, 2026 | ||
| Spreadsheet Reasoning | SpreadsheetBench (test) | 24 | Jun 19, 2026 | ||
| Embodied Decision Making | ALFWorld (test) | 24 | Jun 19, 2026 | ||
| Image Classification | CIFAR-10 | 24 | Jun 19, 2026 | ||
| Image Classification Defense | Tiny-ImageNet | 24 | Jun 19, 2026 | ||
| 3D Object Detection | KITTI (train) | 24 | Jun 19, 2026 | ||
| Question Answering | CSQA | 24 | Jun 30, 2026 | ||
| Algebraic Word Problems | AQuA | 24 | Jun 19, 2026 | ||
| Multi-task Language Understanding | MMLU 153-question shuffled subset | 24 | Jun 19, 2026 | ||
| Science Simulation | ScienceWorld | 24 | Jun 19, 2026 | ||
| Session-based Recommendation | Retailrocket | 24 | Jun 19, 2026 | ||
| Session-based Recommendation | Tmall | 24 | Jun 19, 2026 | ||
| Hate Speech Detection | IHC | 24 | Jun 18, 2026 | ||
| Hate Speech Detection | DYNAHATE | 24 | Jun 18, 2026 | ||
| Skilled Forgery Detection | CEDAR | 24 | Jun 18, 2026 |