Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1010 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Edge Classification | FB15K237 5 way Encyclopedic KG (test) | 27 | Mar 17, 2026 | ||
| Inductive dynamic link prediction | Enron Inductive | 27 | May 29, 2026 | ||
| Machine Unlearning | TOFU Forget 5% | 27 | Mar 16, 2026 | ||
| Image Classification | FACET | 27 | Mar 16, 2026 | ||
| Spectral Risk Optimisation | DGP2 | 27 | Mar 16, 2026 | ||
| Text-to-Image Generation | DrawBench | 27 | Mar 16, 2026 | ||
| Character-Level Language Modeling | Shakespeare (val) | 27 | Apr 2, 2026 | ||
| Optimization | Synthetic quartic function | 27 | Mar 16, 2026 | ||
| Object-Centric Representation Learning | COCO | 27 | Mar 13, 2026 | ||
| Domain names classification | TI Density sequencing 2016 | 27 | Mar 13, 2026 | ||
| Domain names classification | TI Time sequencing 2016 | 27 | Mar 13, 2026 | ||
| Domain names classification | TI Fixed sequencing 2016 | 27 | Mar 13, 2026 | ||
| Open-Set Test-Time Adaptation | Tiny-ImageNet-C | 27 | Apr 3, 2026 | ||
| Compositional Multi-tasking | Compositional Multi-tasking Summarization, Tone Adjustment, Translation (test) | 27 | Mar 13, 2026 | ||
| Synthetic Graph Generation | Planar Dataset | 27 | Mar 31, 2026 | ||
| Injection Attack | Input Reconstruction (All) | 27 | Mar 12, 2026 | ||
| Collision Attack | Input Reconstruction (Mid) | 27 | Mar 12, 2026 | ||
| Collision Attack | Input Reconstruction (First split) | 27 | Mar 12, 2026 | ||
| Inversion Attack | Input Reconstruction (First split) | 27 | Mar 12, 2026 | ||
| PET/CT Report Impression Generation | PET F2I 41K | 27 | Mar 12, 2026 | ||
| Speech-to-Speech Question Answering | Llama Questions | 27 | Apr 21, 2026 | ||
| Visual Discrepancy Detection | OddGridBench | 27 | Mar 11, 2026 | ||
| Content Moderation | MMDS (test) | 27 | Mar 11, 2026 | ||
| Mathematical Reasoning | AMC | 27 | Apr 16, 2026 | ||
| Precise Movement | NavSpace | 27 | Mar 11, 2026 |