Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 640 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Jailbreak Defense | MiniGPT-4 | 36 | Mar 24, 2026 | ||
| Toxicity Defense | MiniGPT-4 | 36 | Mar 24, 2026 | ||
| Cross-view geo-localization | GTA-UAV (Cross-Area) | 36 | May 11, 2026 | ||
| Mathematical Reasoning | Snapask | 36 | Mar 24, 2026 | ||
| General Vision-Language Understanding | LLaVA-OneVision | 36 | Mar 24, 2026 | ||
| Question Answering | BBQ Gender | 36 | Mar 24, 2026 | ||
| Novel View Synthesis | DL3DV 12 views | 36 | Jul 9, 2026 | ||
| Classification | SIM (test) | 36 | Mar 23, 2026 | ||
| Classification | Bank Marketing (BM) (test) | 36 | Mar 23, 2026 | ||
| Classification | Electricity (EL) (test) | 36 | Mar 23, 2026 | ||
| Classification | Covertype (CO) (test) | 36 | Mar 23, 2026 | ||
| Classification | Adult (AD) (test) | 36 | Mar 23, 2026 | ||
| Multi-cluster outbreak control | Asynchronous cluster activation environments | 36 | Mar 23, 2026 | ||
| Instruction Following | MulDimIF | 36 | Apr 6, 2026 | ||
| Text-to-Audio evaluation | PAM (test) | 36 | Mar 23, 2026 | ||
| Hallucination Detection | PubmedQA | 36 | Apr 8, 2026 | ||
| Reward Modeling | PKU-SafeRLHF (test) | 36 | May 8, 2026 | ||
| Information Retrieval | SciFact BEIR | 36 | Jun 29, 2026 | ||
| Regression | diamonds (60% retention) | 36 | Mar 20, 2026 | ||
| Regression | make_regression 60% retention level | 36 | Mar 20, 2026 | ||
| Classification | make_classification | 36 | Mar 20, 2026 | ||
| Classification | Digits | 36 | Mar 20, 2026 | ||
| Time Series Forecasting | 27 real-world application datasets (test) | 36 | Mar 19, 2026 | ||
| Clustering | Artificial data | 36 | Mar 19, 2026 | ||
| Question Answering | NQ | 36 | Mar 18, 2026 |