Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2168 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| PDE Identification | Heat PDE | 16 | May 13, 2026 | ||
| Workflow Steering Defense | ASB-Bench | 16 | May 13, 2026 | ||
| Workflow Steering Defense | MisinfoTask | 16 | May 13, 2026 | ||
| Model Alignment Evaluation | Stoic Alignment Benchmark | 16 | May 13, 2026 | ||
| Persona Alignment | Philosophical Persona Evaluation Set | 16 | May 13, 2026 | ||
| Multi-task Reinforcement Learning | Meta-World MT50 V2 | 16 | May 13, 2026 | ||
| Time Series Classification | UCR 12 | 16 | May 13, 2026 | ||
| Multivariate Time Series Classification | UEA Multivariate 12 datasets (test) | 16 | May 13, 2026 | ||
| Document Retrieval | SciFact BEIR | 16 | May 19, 2026 | ||
| Natural Language Understanding | GLUE | 16 | Jun 30, 2026 | ||
| Binary Classification | CounterAnimal Pair 2: Ptarmigan vs. Prairie-Chicken | 16 | May 13, 2026 | ||
| Binary Classification | CounterAnimal Pair 1: Brambling vs. Bulbul | 16 | May 13, 2026 | ||
| Statement-level classification | BigVul | 16 | May 13, 2026 | ||
| Out-of-Distribution Detection | CIFAR-10 as ID | 16 | May 13, 2026 | ||
| Embodied Task Completion | ALFWorld (IOD) | 16 | May 13, 2026 | ||
| Tabular Data Generation | Beijing | 16 | May 13, 2026 | ||
| Tabular Data Generation | Magic | 16 | May 13, 2026 | ||
| Tabular Data Generation | Shoppers | 16 | May 13, 2026 | ||
| Tabular Data Generation | Default | 16 | May 13, 2026 | ||
| Tabular Data Generation | Adult | 16 | May 13, 2026 | ||
| Robotic Manipulation | LIBERO In-distribution | 16 | May 12, 2026 | ||
| Long-form research | ResearchRubrics | 16 | May 12, 2026 | ||
| Embodied Task Completion | ALFWorld (All tasks) | 16 | May 28, 2026 | ||
| Shape Completion | MedShapeNet (test) | 16 | May 12, 2026 | ||
| Graph Reasoning | GraphInstruct (test) | 16 | May 12, 2026 |