Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 263 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-Agent Reinforcement Learning | SMAC (test) | 63 | Jun 4, 2026 | ||
| Harmfulness detection | BeaverTails, ToxicChat, PKU-SafeRLHF Hard (test) | 63 | May 21, 2026 | ||
| Harmfulness Detection | Full in-distribution (test) | 63 | May 21, 2026 | ||
| Matrix Factorization Utility | Balls-in-Bins accountant n=2048, k=8 | 63 | May 19, 2026 | ||
| Object Detection | DAIR-V2X | 63 | May 19, 2026 | ||
| Behavior decoding | Flint (held-out sessions) | 63 | May 15, 2026 | ||
| Regression | california | 63 | Jun 9, 2026 | ||
| Spatiotemporal traffic forecasting | Milan-Internet | 63 | May 15, 2026 | ||
| Lifelong Model Editing | WikiBigEdit | 63 | May 13, 2026 | ||
| Jailbreak Attack | 159 harmful behaviors (test) | 63 | May 13, 2026 | ||
| Forecasting | Exchange (test) | 63 | May 15, 2026 | ||
| Anomaly Detection | BTAD | 63 | May 25, 2026 | ||
| Anomaly Detection | MPDD | 63 | May 25, 2026 | ||
| Audio Deepfake Detection | WaveFake MelGAN (test) | 63 | May 12, 2026 | ||
| Data Assimilation | Kolmogorov flow short horizon 60 steps | 63 | May 12, 2026 | ||
| Graph Optimization | FORGE-BENCH | 63 | May 12, 2026 | ||
| Mathematical Reasoning | FrontierScience-Olympiad | 63 | May 11, 2026 | ||
| Distillation data detection | S1 | 63 | May 11, 2026 | ||
| End-to-End Defense in RAG | FEVER | 63 | May 4, 2026 | ||
| End-to-End Defense in RAG | ArguAna | 63 | May 4, 2026 | ||
| End-to-End Defense in RAG | FiQA | 63 | May 4, 2026 | ||
| General Reasoning | General Reasoning Suite Average | 63 | May 22, 2026 | ||
| Long-term prediction | NPO-SST | 63 | Apr 28, 2026 | ||
| Long-term prediction | INO-SST | 63 | Apr 28, 2026 | ||
| Text Classification | AGNews | 63 | Apr 24, 2026 |