Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 928 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Malicious Skill Detection | Adversarial Set 400 skills | 28 | Jun 17, 2026 | ||
| Classification | Compas | 28 | Jun 17, 2026 | ||
| Fairness-aware Node Classification | Pokec-n | 28 | Jun 17, 2026 | ||
| Classification | Aggregated | 28 | Jun 17, 2026 | ||
| Classification | Pokec-z | 28 | Jun 17, 2026 | ||
| Node Classification | Aggregated fairness datasets | 28 | Jun 17, 2026 | ||
| Long-term forecasting | ETTm1 | 28 | Jun 16, 2026 | ||
| Open-vocabulary semantic segmentation | Pascal VOC 2012 V21 | 28 | Jun 16, 2026 | ||
| GUI automation | OSWorld | 28 | Jul 7, 2026 | ||
| Text Classification | Call Playbook (test) | 28 | Jun 16, 2026 | ||
| MRI Reconstruction | FastMRI Brain T1 (test) | 28 | Jun 16, 2026 | ||
| MRI Reconstruction | FastMRI Brain T2 (test) | 28 | Jun 16, 2026 | ||
| Odometry | Handheld | 28 | Jun 16, 2026 | ||
| Odometry | Botanic Garden | 28 | Jun 16, 2026 | ||
| Protein-ligand binding affinity prediction | ATOM3D LBA 60% sequence identity | 28 | Jun 15, 2026 | ||
| State Estimation | Lorenz-96 | 28 | Jun 15, 2026 | ||
| Human Activity Recognition | WISDM Cross-person split | 28 | Jun 15, 2026 | ||
| Human Activity Recognition | OPPORTUNITY Cross-person | 28 | Jun 15, 2026 | ||
| Human Activity Recognition | DSADS Cross-person | 28 | Jun 15, 2026 | ||
| Cross-Position Human Activity Recognition | PAMAP2 | 28 | Jun 15, 2026 | ||
| Image Classification | Pets | 28 | Jun 12, 2026 | ||
| Downstream Classification | ACS data (test) | 28 | Jun 12, 2026 | ||
| Distribution Fidelity | ACS | 28 | Jun 12, 2026 | ||
| Machine Translation | WMT 14 | 28 | Jun 11, 2026 | ||
| Text Summarization | CNNDM | 28 | Jun 11, 2026 |