Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1807 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-view Clustering | CCV 20 | 18 | Jun 4, 2026 | ||
| Multi-view Clustering | Scene15 | 18 | Jun 4, 2026 | ||
| MIME classification | MAGIC-FILES network-capture (cleartext UDP) (n = 498 streams) | 18 | Jun 4, 2026 | ||
| Zero-shot Evaluation | Zero-Shot Aggregate | 18 | Jun 4, 2026 | ||
| Hallucination Evaluation | TBH (ToolBench Hallucination) | 18 | Jun 4, 2026 | ||
| Safety Evaluation | Safety Benchmarks ASB, InjecAgent, AHarm, ASecBench | 18 | Jun 4, 2026 | ||
| Capacitated Vehicle Routing Problem (CVRP) | Synthetic CVRP10K | 18 | Jun 4, 2026 | ||
| Traveling Salesman Problem (TSP) | Synthetic TSP10K | 18 | Jun 4, 2026 | ||
| Image Reconstruction | PIE (test) | 18 | Jun 4, 2026 | ||
| Image Reconstruction | PIE (train) | 18 | Jun 4, 2026 | ||
| Image Reconstruction | Yale B (test) | 18 | Jun 4, 2026 | ||
| Image Reconstruction | Yale B (train) | 18 | Jun 4, 2026 | ||
| Action Recognition | Walking Running database 2-class | 18 | Jun 4, 2026 | ||
| Image Filtering | Barbara (test) | 18 | Jun 4, 2026 | ||
| Adversarial Robustness | CIFAR-100 | 18 | Jun 4, 2026 | ||
| Mathematical Reasoning | Minerva | 18 | Jun 23, 2026 | ||
| Interactive Decision-Making | ALFWorld (OOD) | 18 | Jun 4, 2026 | ||
| Time Series Classification | MedicalImages (MImg) | 18 | Jun 4, 2026 | ||
| Wide-Baseline Correspondence Reasoning | ReasonMatch-Bench Overall 90-sample high-divergence subset | 18 | Jun 4, 2026 | ||
| Mathematics Reasoning | GSM8K | 18 | Jun 8, 2026 | ||
| Multi-Object Tracking | UniRTL | 18 | Jun 4, 2026 | ||
| Model Stealing | Mutagenicity | 18 | Jun 4, 2026 | ||
| Inpaint (box) | FFHQ 256 x 256 | 18 | Jun 30, 2026 | ||
| Annotator Modeling | agnews | 18 | Jun 4, 2026 | ||
| Annotator Modeling | dtd | 18 | Jun 4, 2026 |