Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1835 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Visual Object Tracking | VOT 2020 | 18 | May 27, 2026 | ||
| Partially Relevant Video Retrieval | Charades-STA | 18 | May 8, 2026 | ||
| Text-based embodied task completion | ALFWorld | 18 | May 8, 2026 | ||
| Speech-driven gesture generation | BEAT2 (Seen Speakers) | 18 | May 8, 2026 | ||
| Object Detection | PASCALRAW Overexposed | 18 | May 11, 2026 | ||
| Anomaly Detection | RESC BMAD (test) | 18 | May 8, 2026 | ||
| Anomaly Detection | BraTS BMAD 2021 (test) | 18 | May 8, 2026 | ||
| Temporal Segmentation | Keck | 18 | May 8, 2026 | ||
| Temporal Segmentation | Weizmann | 18 | May 8, 2026 | ||
| Human Motion Segmentation | UT | 18 | May 8, 2026 | ||
| Continual learning | Math-LLM ScienceQA, NumGLUE-cm, NumGLUE-ds | 18 | Jun 29, 2026 | ||
| Question Answering | SSP Evaluation Suite (NQ, TriviaQA, PopQA, HotpotQA, 2WikiMultiHopQA, MuSiQue, Bamboogle) Judge model DeepSeek-V3 V3.2 | 18 | May 8, 2026 | ||
| Sparse-view 3D reconstruction | S2C-Scene (test) | 18 | May 8, 2026 | ||
| Sparse-view 3D reconstruction | Replica (test) | 18 | May 8, 2026 | ||
| Sparse-view 3D reconstruction | ScanNet++ (test) | 18 | May 8, 2026 | ||
| Multi-image Dialogue Understanding | MMDU | 18 | Jul 2, 2026 | ||
| Large Audio-Language Model Safety Evaluation | Figstep audio | 18 | May 8, 2026 | ||
| Classification | OrganAMNIST | 18 | May 8, 2026 | ||
| Classification | OCTMNIST | 18 | May 8, 2026 | ||
| Classification | CIFAR-10 | 18 | May 8, 2026 | ||
| Classification | FashionMNIST | 18 | May 8, 2026 | ||
| Classification | OrganAMNIST | 18 | May 8, 2026 | ||
| Classification | OCTMNIST | 18 | May 8, 2026 | ||
| Classification | CIFAR-10 | 18 | May 8, 2026 | ||
| Classification | FashionMNIST | 18 | May 8, 2026 |