Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1425 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Visual Object Tracking | GOT-10k Foggy | 21 | Jul 2, 2026 | ||
| Long-context memory evaluation | LoCoMo full | 21 | Jul 2, 2026 | ||
| Anomaly Detection | Swan | 21 | Jul 2, 2026 | ||
| Anomaly Detection | SWaT | 21 | Jul 2, 2026 | ||
| Unconditional Image Unlearning | CelebA-HQ (test) | 21 | Jul 1, 2026 | ||
| Multi-hop spatial reasoning | StepGame (test) | 21 | Jul 1, 2026 | ||
| Satellite Image Synthesis | Git-Dense 3.5k | 21 | Jul 1, 2026 | ||
| Decision Making | ALFWorld, WebShop, ScienceWorld, BabyAI (test) | 21 | Jun 30, 2026 | ||
| Image Classification | CIFAR-10N Worst noise | 21 | Jun 30, 2026 | ||
| Image Classification | CIFAR-10N Random 1 noise | 21 | Jun 30, 2026 | ||
| Image Classification | CIFAR-10N Aggregate noise | 21 | Jun 30, 2026 | ||
| Table Parsing | Average OmniDocBench CC-OCR OCRBench V2 TableVerse-5K | 21 | Jun 30, 2026 | ||
| Table Parsing | TableVerse-5K | 21 | Jun 30, 2026 | ||
| Table Parsing | OCRBench V2 | 21 | Jun 30, 2026 | ||
| Table Parsing | CC-OCR | 21 | Jun 30, 2026 | ||
| Table Parsing | OmniDocBench | 21 | Jun 30, 2026 | ||
| Light Attribute Prediction | MLE (test) | 21 | Jun 30, 2026 | ||
| Language-guided Visual Tracking | LaSOT | 21 | Jun 30, 2026 | ||
| Computer Vision General Capability Evaluation | CV-Bench | 21 | Jun 30, 2026 | ||
| Micro-expression Recognition | SMIC-HS | 21 | Jun 29, 2026 | ||
| Regression | Geospatial tasks Regression | 21 | Jun 29, 2026 | ||
| Classification | Geospatial tasks | 21 | Jun 29, 2026 | ||
| Trajectory Prediction | Argoverse (leaderboard) | 21 | Jun 29, 2026 | ||
| Text-to-Image Compositional Reasoning | SugarCrepe++ TOT | 21 | Jun 26, 2026 | ||
| Image-to-Text Compositional Reasoning | SugarCrepe++ ITT | 21 | Jun 26, 2026 |