Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1537 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question Answering and Reasoning | ARC Mean of Easy and Challenge | 20 | Jun 16, 2026 | ||
| Jailbreak Safety Evaluation | PAP | 20 | Jun 16, 2026 | ||
| Jailbreak Safety Evaluation | Multi-Shot Jailbreak (MSJ) | 20 | Jun 16, 2026 | ||
| Harmful Content Safety Evaluation | XsTest Harmful | 20 | Jun 16, 2026 | ||
| Harmful Content Safety Evaluation | HexPHI | 20 | Jun 16, 2026 | ||
| Harmful Content Safety Evaluation | AdvBench | 20 | Jun 16, 2026 | ||
| Contextual stochastic optimization | Synthetic controlled portfolio sweep (Hardest 25%) | 20 | Jun 16, 2026 | ||
| Contextual stochastic optimization | Controlled portfolio sweep synthetic (test) | 20 | Jun 16, 2026 | ||
| Voice Conversion | LibriSpeech Clean 100 source and target longer than 1 min | 20 | Jun 16, 2026 | ||
| NMPC optimization | NMPC Ntest = 5000 (test) | 20 | Jun 16, 2026 | ||
| PDE Solving | RealPDEBench Turbulent Combustion 1.0 (test) | 20 | Jun 16, 2026 | ||
| PDE Solving | RealPDEBench Controlled Cylinder 1.0 (test) | 20 | Jun 16, 2026 | ||
| PDE Solving | RealPDEBench Cylinder Flow 1.0 (test) | 20 | Jun 16, 2026 | ||
| Model Merging | 7-task NLP benchmark | 20 | Jun 16, 2026 | ||
| Personalized Federated Learning Unlearning | FEMNIST (natural partition) | 20 | Jun 16, 2026 | ||
| Personalized Federated Learning Unlearning | CIFAR-100 alpha_dir = 0.5 | 20 | Jun 16, 2026 | ||
| Personalized Federated Learning Unlearning | CIFAR-10 alpha_dir = 0.5 | 20 | Jun 16, 2026 | ||
| Mathematical Reasoning | MATH (test) | 20 | Jun 16, 2026 | ||
| Node Classification | Ogbn-arxiv Non-Evolving | 20 | Jun 16, 2026 | ||
| Novel View Synthesis | Tanks & Temples | 20 | Jul 7, 2026 | ||
| Tool-use | AgentHarm (public test) | 20 | Jun 16, 2026 | ||
| OS assistance | Safe-OS system-sabotage and environment-dependent | 20 | Jun 16, 2026 | ||
| Web navigation | Mind2Web-SC | 20 | Jun 16, 2026 | ||
| Web browsing | WebShop | 20 | Jun 16, 2026 | ||
| Personalized Public Transit Routing | Personalized Public Transit Routing Short Journeys (test) | 20 | Jun 16, 2026 |