Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1196 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Molecular Dynamics Simulation | 2N5C (test) | 24 | Apr 29, 2026 | ||
| Physical dynamics simulation | Charged | 24 | Apr 29, 2026 | ||
| Physical dynamics simulation | Spring | 24 | Apr 29, 2026 | ||
| Spatio-temporal forecasting | Covid | 24 | Apr 29, 2026 | ||
| Spatio-temporal forecasting | Motion | 24 | Apr 29, 2026 | ||
| Concept Monitoring | 11 concept monitoring tasks (test) | 24 | Apr 28, 2026 | ||
| Multimodal Hallucination Evaluation | MME | 24 | Jun 30, 2026 | ||
| Adversarial Image Classification | CIFAR-100 | 24 | Apr 28, 2026 | ||
| Few-shot Classification | OSDG2 | 24 | Apr 28, 2026 | ||
| Few-shot Classification | OSDG 1 | 24 | Apr 28, 2026 | ||
| Few-shot Classification | OSDG2 (test) | 24 | Apr 28, 2026 | ||
| Few-shot Classification | OSDG1 (test) | 24 | Apr 28, 2026 | ||
| Attributed Question Answering | ALCE | 24 | Apr 28, 2026 | ||
| Multi-hop Question Answering | MultihopQA | 24 | Apr 28, 2026 | ||
| Jailbreak Attack | AdvBench Text | 24 | Apr 28, 2026 | ||
| Image Classification | ImageNet 1K | 24 | Apr 28, 2026 | ||
| Model Merging | Sustainability to large-scale tasks | 24 | Apr 28, 2026 | ||
| Model Merging | Sustainability to large-scale tasks 2 tasks | 24 | Apr 28, 2026 | ||
| Image Classification | Corrupted (test) | 24 | Apr 28, 2026 | ||
| Image Classification | CIFAR10 (test) | 24 | Apr 28, 2026 | ||
| Image Classification | MNIST (test) | 24 | Apr 28, 2026 | ||
| Memory Attack | CSQA | 24 | Apr 28, 2026 | ||
| Physical Red Teaming | RedVLA Conditional-Level Scenarios | 24 | Apr 27, 2026 | ||
| MRI Reconstruction | FastMRI Knee (OOD) | 24 | Apr 27, 2026 | ||
| MRI Reconstruction | FastMRI Brain (OOD) | 24 | Apr 27, 2026 |