Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 591 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Object Detection | M3FD (test) | 38 | Mar 27, 2026 | ||
| Goal reasoning | EgoToM | 38 | Mar 26, 2026 | ||
| Speech Enhancement | Ad-hoc microphone array 4-channel (test) | 38 | Mar 27, 2026 | ||
| Partially Relevant Video Retrieval | ActivityNet Captions | 38 | May 8, 2026 | ||
| Node Classification | ETH-Large | 38 | Mar 26, 2026 | ||
| Node Classification | ETH Small | 38 | Mar 26, 2026 | ||
| Mathematical Word Problem Solving | SVAMP | 38 | May 27, 2026 | ||
| Anomaly Detection | Eyecandies | 38 | Apr 28, 2026 | ||
| 3D placement | 3D placement benchmark | 38 | Mar 25, 2026 | ||
| Anomaly Detection | KR | 38 | Mar 24, 2026 | ||
| Open-vocabulary semantic segmentation | Pascal VOC 20 without background | 38 | May 13, 2026 | ||
| Text-to-Audio evaluation | RELATE (test) | 38 | Mar 23, 2026 | ||
| Trajectory Planning | NavSim (test) | 38 | Jun 17, 2026 | ||
| Reward Modeling | UltraFeedback (test) | 38 | May 8, 2026 | ||
| Object Detection | SSDD | 38 | Jun 25, 2026 | ||
| Mathematical Reasoning | GPQA | 38 | Jun 18, 2026 | ||
| Translation Evaluation | Met-BOUQuET XSTS+R+P (test) | 38 | Mar 18, 2026 | ||
| Multi-turn instruction following | SysBench | 38 | Apr 21, 2026 | ||
| Image Classification | ImageNet A, V, R, S (val) | 38 | Mar 18, 2026 | ||
| MRI Synthesis | BraTS 2023 | 38 | Apr 2, 2026 | ||
| Panoramic Image Quality Assessment | OIQA (test) | 38 | Apr 28, 2026 | ||
| Cross-view Geo-localization (Satellite to Drone) | SUES-200 250m altitude | 38 | May 12, 2026 | ||
| Image Compression | CLIC 2020 | 38 | Jun 23, 2026 | ||
| Query-Answering | PersonaMem 1M context length | 38 | May 7, 2026 | ||
| Out-of-domain OOD detection | 8 single-domain benchmarks average | 38 | Mar 13, 2026 |