Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1861 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Time Series Classification | 18 UEA datasets 50% Missing | 18 | Apr 3, 2026 | ||
| Classification | BasicMotions (Average) | 18 | Apr 3, 2026 | ||
| Classification | BasicMotions 70% Missing | 18 | Apr 3, 2026 | ||
| Classification | BasicMotions (30% Missing) | 18 | Apr 3, 2026 | ||
| Classification | BasicMotions Regular (0% missingness) | 18 | Apr 3, 2026 | ||
| Membership Inference Attack (TEXTLEN=64) | VL-MIA TEXT | 18 | Apr 2, 2026 | ||
| Persona Alignment | Dignity Peer Persona Dimensions | 18 | Apr 2, 2026 | ||
| Video Instance Segmentation | YTVIS 2021 (test val) | 18 | Apr 2, 2026 | ||
| Image Classification | ImageNet | 18 | Apr 2, 2026 | ||
| Point Map Reconstruction | DL3DV-benchmark 8-view | 18 | Apr 2, 2026 | ||
| Novel View Synthesis | N3V datasets | 18 | Apr 2, 2026 | ||
| Unlearning | HumanEval State unlearning | 18 | Apr 2, 2026 | ||
| Environment Unlearning | HotPotQA | 18 | Apr 2, 2026 | ||
| Environment Unlearning | GridWorld | 18 | Apr 2, 2026 | ||
| Trajectory Unlearning | AlfWorld | 18 | Apr 2, 2026 | ||
| Action Recognition | NTU RGB+D 120 (Cross-Subject 96/24) | 18 | Apr 2, 2026 | ||
| Criteria-conditioned Clustering | Fruit-2c OpenSMC | 18 | Apr 2, 2026 | ||
| Criteria-conditioned Clustering | Card-2c OpenSMC | 18 | Apr 2, 2026 | ||
| Continual Learning | VDD | 18 | Apr 2, 2026 | ||
| Continual Learning | MTIL | 18 | Apr 2, 2026 | ||
| Math reasoning | MATH500 | 18 | Apr 13, 2026 | ||
| Scientific Image Synthesis | Science-T2I (test) | 18 | Apr 2, 2026 | ||
| Remote Sensing Downstream Tasks | Pangaea benchmark | 18 | Apr 2, 2026 | ||
| Semantic Segmentation | Pangaea benchmark | 18 | Apr 2, 2026 | ||
| Goal Alignment | PPS-Bench Mean across languages | 18 | Apr 1, 2026 |