Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 619 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Object Detection | DOTA v1.5 | 37 | Feb 26, 2026 | ||
| Trajectory Prediction | nuScenes Prediction Challenge (test) | 37 | Feb 26, 2026 | ||
| Transductive Node Classification | Cora 20 labels per class | 37 | Feb 26, 2026 | ||
| Semantic Correspondence | PF-WILLOW (test) | 37 | Feb 26, 2026 | ||
| Semantic Segmentation | DADA-seg (test) | 37 | Feb 26, 2026 | ||
| Novel View Synthesis | Blender (test) | 37 | Feb 26, 2026 | ||
| Credit approval prediction | Credit Approval dataset (test) | 37 | Feb 26, 2026 | ||
| Node classification | arXiv-year 50/25/25 (test) | 37 | Feb 26, 2026 | ||
| Spoof Speech Detection | ASVspoof LA 2021 (eval) | 37 | Jul 7, 2026 | ||
| 3D Pose Estimation | Shelf | 37 | Jun 8, 2026 | ||
| Audio-visual Classification | VGGSound | 37 | Apr 10, 2026 | ||
| Zero-Shot Learning | AWA2 (unseen) | 37 | Feb 26, 2026 | ||
| Online Action Detection | THUMOS '14 | 37 | Mar 4, 2026 | ||
| Sentence Simplification | ASSET English (test) | 37 | Feb 26, 2026 | ||
| Logical Reasoning | ReClor Hard (test) | 37 | Feb 26, 2026 | ||
| Referring Expression Grounding | RefCOCOg (test) | 37 | Jun 9, 2026 | ||
| Semantic Segmentation | SYNTHIA to Cityscapes 13-class | 37 | Feb 26, 2026 | ||
| RGB-D Salient Object Detection | SIP (test) | 37 | Feb 26, 2026 | ||
| Video Action Recognition | HMDB-51 | 37 | Feb 26, 2026 | ||
| Depth Prediction | ETH3D | 37 | Mar 24, 2026 | ||
| Generalized Few-Shot Learning | AWA Two-Level distributions (test) | 37 | Feb 26, 2026 | ||
| Generalized Few-Shot Learning | CUB Two-Level distributions (test) | 37 | Feb 26, 2026 | ||
| Named Entity Recognition | NCBI-disease | 37 | Apr 14, 2026 | ||
| Passage retrieval | WebQuestions (WQ) (test) | 37 | Feb 26, 2026 | ||
| Knowledge Tracing | ASSIST12 | 37 | May 12, 2026 |