Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2092 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 3D Face Reconstruction | NoW | 17 | Feb 26, 2026 | ||
| Tumor Segmentation | LiTS | 17 | Feb 26, 2026 | ||
| Question Answering | HybridQA (dev) | 17 | Feb 26, 2026 | ||
| Intent Classification | SciCite (test) | 17 | Feb 26, 2026 | ||
| Morphological Tagging | PDT 3.5 (test) | 17 | Feb 26, 2026 | ||
| OOD Detection | CIFAR-10 standard (test) | 17 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL Gym walker2d (full-replay) | 17 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL Gym halfcheetah (full-replay) | 17 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL Adroit relocate v0 (cloned) | 17 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL Adroit pen v0 (cloned) | 17 | Feb 26, 2026 | ||
| AMR-to-text | LDC2017T10 AMR17 (test) | 17 | Feb 26, 2026 | ||
| Anomaly Detection | Fishyscapes Web Oct 20 | 17 | Feb 27, 2026 | ||
| Salient Object Detection | STEREO797 | 17 | Feb 26, 2026 | ||
| Salient Object Detection | STEREO797 (test) | 17 | Feb 26, 2026 | ||
| Anomaly Detection | AITEX (test) | 17 | Apr 21, 2026 | ||
| Cross-contrast MR image translation | IXI (test) | 17 | Feb 26, 2026 | ||
| CTR Prediction | Malware | 17 | Feb 26, 2026 | ||
| 3D Human Pose Estimation | MPI-INF-3DHP | 17 | Feb 26, 2026 | ||
| 3D Human Pose Estimation | Human3.6M H36MA | 17 | Apr 30, 2026 | ||
| Referring Expression Comprehension | Flickr30K Entities (test) | 17 | Feb 26, 2026 | ||
| Time Series Forecasting | M4 Weekly | 17 | Apr 13, 2026 | ||
| End-to-End Text Spotting | ReCTS (test) | 17 | Feb 26, 2026 | ||
| Animal species (186 classes). Domains: 324 camera locations. | iWildCam WILDS (test) | 17 | Feb 26, 2026 | ||
| Speech Translation | MuST-C EN-FR COMMON (test) | 17 | Feb 26, 2026 | ||
| Data-to-Text Generation | WikiBio (test) | 17 | Feb 27, 2026 |