Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 516 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Argument Classification | ERE-EN (dev) | 42 | Feb 26, 2026 | ||
| Keyphrase extraction | SemEval 2017 | 42 | May 4, 2026 | ||
| Object Detection | KITTI to Cityscapes | 42 | Feb 26, 2026 | ||
| Topic Classification | Yahoo | 42 | Feb 26, 2026 | ||
| Novel View Synthesis | ReNe 1.0 (hard) | 42 | Feb 26, 2026 | ||
| Novel View Synthesis | ReNe easy 1.0 | 42 | Feb 26, 2026 | ||
| Multi-view Clustering | Synthetic3d | 42 | May 18, 2026 | ||
| Named Entity Recognition | ACE 2005 | 42 | Apr 20, 2026 | ||
| Named Entity Recognition | Broad Twitter Corpus | 42 | Apr 20, 2026 | ||
| Sleep Staging | SHHS 1 (test) | 42 | Feb 26, 2026 | ||
| Text-to-Video Retrieval | MSRVTT (1K-A) | 42 | Feb 27, 2026 | ||
| Action Recognition | Kinetics-400 | 42 | Apr 21, 2026 | ||
| 3D Human Mesh Estimation | 3DPW | 42 | Feb 26, 2026 | ||
| Semantic Segmentation | COCO-Stuff without background class | 42 | Apr 29, 2026 | ||
| Question Answering | TruthfulQA | 42 | Feb 26, 2026 | ||
| Semantic Segmentation | ADE | 42 | May 8, 2026 | ||
| Natural Language Inference | RTE | 42 | Feb 27, 2026 | ||
| Commonsense Reasoning | Winogrande | 42 | Feb 27, 2026 | ||
| Node Classification | Cornell h=0.3 (test) | 42 | Feb 26, 2026 | ||
| Node Classification | Citeseer h=0.74 (test) | 42 | Feb 26, 2026 | ||
| Node Classification | Cora h=0.81 (test) | 42 | Feb 26, 2026 | ||
| Joint Multiple Intent Detection and Slot Filling | MixATIS (test) | 42 | Feb 26, 2026 | ||
| Action Detection | AVA v2.2 | 42 | Feb 26, 2026 | ||
| Multi-Agent Reinforcement Learning | TREA rdist | 42 | Feb 26, 2026 | ||
| Action Recognition | UCF101 (val) | 42 | Feb 26, 2026 |