Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 76 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Hallucination detection | NQ-Open | 141 | Jun 19, 2026 | ||
| Time Series Forecasting | ILI | 141 | May 21, 2026 | ||
| Sentiment Analysis | CR | 141 | Mar 5, 2026 | ||
| 5-way Few-shot Classification | Mini-ImageNet (test) | 141 | Feb 27, 2026 | ||
| 3D Human Pose Estimation | 3DPW | 141 | Jun 30, 2026 | ||
| Action Recognition | Kinetics-400 full (val) | 141 | Mar 17, 2026 | ||
| Visual Dialog | VisDial v0.9 (val) | 141 | Feb 26, 2026 | ||
| Image Quality Assessment | TID 2013 (test) | 141 | Apr 23, 2026 | ||
| Text Classification | IMDB | 141 | Jun 4, 2026 | ||
| Image Classification | MNIST (train) | 141 | Jun 9, 2026 | ||
| Generalized Referring Expression Segmentation | gRefCOCO (testB) | 141 | May 29, 2026 | ||
| Vision Understanding | MMBench | 141 | Jul 7, 2026 | ||
| Weather Forecasting | WeatherBench ERA5 (test) | 140 | May 20, 2026 | ||
| Drug perturbation response prediction | 4i 20% (test) | 140 | Apr 30, 2026 | ||
| Safety Evaluation | HexPhi | 140 | Apr 24, 2026 | ||
| Novelty Recommendation | ModCloth | 140 | Apr 10, 2026 | ||
| Image Classification | Waterbirds In-context training: iNaturalist (test) | 140 | Apr 3, 2026 | ||
| Image Deblurring | CBSD68 (val) | 140 | Mar 26, 2026 | ||
| Semantic Segmentation | Cityscapes | 140 | Jul 9, 2026 | ||
| Text-to-image generation | Stable Diffusion 1.4 | 140 | Mar 17, 2026 | ||
| Code Generation | HumanEval | 140 | Jun 19, 2026 | ||
| Physical parameter regression | Chandra Source Catalog (CSC) (val) | 140 | Mar 6, 2026 | ||
| Multimodal Hallucination Evaluation | MMHal-Bench | 140 | Jun 26, 2026 | ||
| Long-term Time Series Forecasting | Exchange | 140 | May 21, 2026 | ||
| Model Reduction | Burgers' Equation Shift Trajectory Manifold | 140 | Feb 26, 2026 |