Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1402 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Zero-shot Image Classification | ImageNet shift | 22 | Feb 26, 2026 | ||
| Part Segmentation | PASCAL-PART | 22 | Mar 31, 2026 | ||
| PointGoal navigation | iGibson Env Avg 1.0 (test) | 22 | Feb 26, 2026 | ||
| PointGoal navigation | iGibson Rs int 1.0 (test) | 22 | Feb 26, 2026 | ||
| PointGoal navigation | iGibson Ihlen 0 int 1.0 (test) | 22 | Feb 26, 2026 | ||
| Object Detection | CSD | 22 | Mar 10, 2026 | ||
| Anomaly Detection | ELPV | 22 | Feb 26, 2026 | ||
| Event-based action recognition | HARDVS | 22 | Feb 26, 2026 | ||
| Named Entity Recognition | ACE04 | 22 | May 13, 2026 | ||
| 3D whole-body human pose and shape estimation | AGORA SMPL-X (test) | 22 | Feb 26, 2026 | ||
| Natural Language Inference | MNLI | 22 | Feb 26, 2026 | ||
| Verb Recognition | Epic-Kitchens (EK) | 22 | Feb 27, 2026 | ||
| Image Denoising | BSD68 (test) | 22 | Feb 26, 2026 | ||
| Mathematical Reasoning | MMLU STEM (test) | 22 | Feb 26, 2026 | ||
| Closed-set Source-Free Domain Adaptation | Office-Home | 22 | Feb 26, 2026 | ||
| Image Super-Resolution | 2K (test) | 22 | Jun 19, 2026 | ||
| Image Generation | MS-COCO 30K (val) | 22 | Feb 26, 2026 | ||
| Video Super-Resolution | ZeroDay (test) | 22 | Feb 26, 2026 | ||
| Near-OOD Detection | Tiny ImageNet Near-OOD (test) | 22 | Feb 26, 2026 | ||
| Camera Relocalization | Cambridge Landmarks (test) | 22 | Feb 26, 2026 | ||
| Rule Alignment Evaluation | RuLES | 22 | Feb 26, 2026 | ||
| Safety Evaluation | HH-RedTeaming | 22 | Feb 26, 2026 | ||
| Multivariate Time Series Classification | Atrial Fibrillation | 22 | Feb 26, 2026 | ||
| Multivariate Time Series Classification | ERing | 22 | Feb 26, 2026 | ||
| Multivariate Time Series Classification | DuckDuckGeese | 22 | Jun 4, 2026 |