Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 90 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Next Action Prediction | User-specific next action prediction dataset 20 users 1.0 (Individual Users and Mean Performance) | 126 | Mar 9, 2026 | ||
| High-resolution perception | HR Bench 4K | 126 | Jul 2, 2026 | ||
| Autonomous Driving Planning | NAVSIM v1 | 126 | May 21, 2026 | ||
| Regression | Dst index (test) | 126 | Feb 26, 2026 | ||
| Clustering | LandUse-21 | 126 | Jun 4, 2026 | ||
| Structured Web Data Extraction | SWDE | 126 | May 6, 2026 | ||
| Math | MATH-500 | 126 | Jun 26, 2026 | ||
| Math Reasoning | GSM8K | 126 | Feb 26, 2026 | ||
| Video generation | VBench | 126 | Mar 9, 2026 | ||
| Image Quality Assessment | KonIQ-10k | 126 | Apr 14, 2026 | ||
| Long-term Time Series Forecasting | Solar-Energy | 126 | May 19, 2026 | ||
| Logical Reasoning | FOLIO | 126 | May 11, 2026 | ||
| Base-to-New Generalization | FGVCAircraft | 126 | Jul 8, 2026 | ||
| Novel View Synthesis | MipNeRF 360 Indoor | 126 | May 11, 2026 | ||
| Time Series Imputation | ETTh2 | 126 | Jul 9, 2026 | ||
| Skeleton-based Action Recognition | NTU RGB+D 60 (X-View) | 126 | Feb 26, 2026 | ||
| Environmental sound classification | FSD50K | 126 | Jun 4, 2026 | ||
| Speaker Recognition | VoxCeleb1 (test) | 126 | Feb 26, 2026 | ||
| Node Classification | DBLP | 126 | May 14, 2026 | ||
| Text Detection | Total-Text (test) | 126 | Feb 26, 2026 | ||
| Monocular Depth Estimation | KITTI 80m maximum depth (Eigen) | 126 | Feb 26, 2026 | ||
| Node Classification | PPI (test) | 126 | May 19, 2026 | ||
| Object Detection | PASCAL VOC | 126 | May 13, 2026 | ||
| Molecular Property Prediction | MoleculeNet BACE (scaffold) | 126 | Jun 25, 2026 | ||
| Multivariate Forecasting | Electricity | 126 | Jul 8, 2026 |