Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 615 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Traveling Salesman Problem | TSP100 | 37 | May 26, 2026 | ||
| Graph Classification | BZR_MD to BZR (target) | 37 | Apr 6, 2026 | ||
| Graph Classification | BZR to BZR_MD (target) | 37 | Apr 6, 2026 | ||
| Aerial Visual Localization | UAVD4L LoD (out-of-Traj.) | 37 | Jun 29, 2026 | ||
| Aerial Visual Localization | UAVD4L LoD (in-Traj.) | 37 | Jun 29, 2026 | ||
| Fraud Detection | Credit Card Fraud dataset | 37 | May 21, 2026 | ||
| Table Structure Recognition | PubTabNet | 37 | Jun 24, 2026 | ||
| Visual Question Answering | VizWizQA | 37 | Mar 17, 2026 | ||
| Audio Deepfake Detection | ASVspoof 2019 | 37 | Apr 16, 2026 | ||
| Semantic Segmentation | ACDC Fog | 37 | May 8, 2026 | ||
| Multi-source Domain Generalization | PACS | 37 | Jun 23, 2026 | ||
| Face Image Quality Assessment | CGFIQA-40k (test) | 37 | Feb 26, 2026 | ||
| Unconditional Image Generation | AFHQ 64x64 v2 (test) | 37 | Mar 13, 2026 | ||
| Natural Language Understanding | GLUE and SuperGLUE (test val) | 37 | Feb 26, 2026 | ||
| Multivariate long-term forecasting | ETTh1 T=192 (test) | 37 | Feb 26, 2026 | ||
| Multi-sound source localization | VGGSound-Duet (test) | 37 | Apr 10, 2026 | ||
| Multi-sound source localization | MUSIC-Duet (test) | 37 | Apr 10, 2026 | ||
| Novel View Synthesis | GSO | 37 | Jul 7, 2026 | ||
| Image Classification | CIFAR10 | 37 | Feb 27, 2026 | ||
| Point-Goal Navigation | Gibson (held-out scenes) | 37 | Mar 6, 2026 | ||
| Comprehensive Examination | AGIEval (test) | 37 | May 19, 2026 | ||
| Visual Place Recognition | SVOX Rain | 37 | Feb 26, 2026 | ||
| Person Re-identification | CARGO Protocol 2: G↔G 1.0 | 37 | May 19, 2026 | ||
| Multi-Object Tracking | BFT 1.0 (test) | 37 | Feb 26, 2026 | ||
| Closed-set Source-Free Domain Adaptation | VisDA Sy→Re | 37 | Feb 26, 2026 |