Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 547 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Microscopic weight completion | HTT | 40 | Apr 1, 2026 | ||
| Image Classification | Plankton (test) | 40 | Apr 1, 2026 | ||
| Function approximation | Bratley Sum D=250 | 40 | Apr 1, 2026 | ||
| Function approximation | Bratley Sum D=100 | 40 | Apr 1, 2026 | ||
| Global Localization | Garden LT | 40 | Apr 1, 2026 | ||
| Reinforcement Learning Control | Pendulum v1 | 40 | Apr 1, 2026 | ||
| Scientific Agent Task Completion | ScienceAgentBench | 40 | Apr 28, 2026 | ||
| High-Resolution Multimodal Reasoning | HR-Bench 4K | 40 | Apr 14, 2026 | ||
| High-Resolution Multimodal Reasoning | HR-Bench 8K | 40 | Apr 14, 2026 | ||
| Image-to-CAD program synthesis | GenCAD (test) | 40 | Mar 31, 2026 | ||
| Safety Alignment | Visual Adversarial Attacks | 40 | Mar 30, 2026 | ||
| Safety Alignment | JOOD | 40 | Mar 30, 2026 | ||
| Fleet Requirement Estimation | Stockholm city center network | 40 | Mar 30, 2026 | ||
| Model Fingerprinting | Fashion-MNIST | 40 | Mar 27, 2026 | ||
| Jailbreak Defense | AdvBench PAD | 40 | Mar 27, 2026 | ||
| Multi-Objective Reinforcement Learning | Amsterdam transport planning environment | 40 | Mar 27, 2026 | ||
| Watermark Detection | Aya-23 8B 10 unsupported languages | 40 | Mar 26, 2026 | ||
| OOD Detection | ImageNet-1k (ID) vs SUN (OOD) | 40 | May 26, 2026 | ||
| Object Recognition | ModelNet40 5-way | 40 | Mar 26, 2026 | ||
| Short-term wildfire danger forecasting | Mesogeos | 40 | Mar 26, 2026 | ||
| Task Planning | EB-ALFRED Base | 40 | Apr 21, 2026 | ||
| Refusal Ablation and Jailbreak Attack Success | HARMBENCH | 40 | Mar 25, 2026 | ||
| Energy demand forecasting | AEP | 40 | Jun 17, 2026 | ||
| Image Extrapolation | Remote Sensing Image Extrapolation | 40 | Mar 24, 2026 | ||
| Machine-generated text detection | XSum | 40 | Apr 21, 2026 |