Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1207 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Video Question Answering | MovieChat | 24 | May 12, 2026 | ||
| Video Captioning | Video Detail Description (VDD) | 24 | Apr 8, 2026 | ||
| Video Captioning | Video Detail Caption (VDC) | 24 | Apr 8, 2026 | ||
| Jailbreaking | EHRAgent ALL | 24 | Apr 8, 2026 | ||
| Video Question Answering | VideoAgent Aggregate: EgoSchema and NExT-QA | 24 | Apr 8, 2026 | ||
| Text Summarization | Text Summarization | 24 | Apr 8, 2026 | ||
| Code Retrieval | MTEB Code Retrieval Average (val) | 24 | Apr 8, 2026 | ||
| Code Retrieval | FreshStack (val) | 24 | Apr 8, 2026 | ||
| Code Retrieval | DS10K (val) | 24 | Apr 8, 2026 | ||
| Code Retrieval | MBPP (val) | 24 | Apr 8, 2026 | ||
| Code Retrieval | HumanEval (val) | 24 | Apr 8, 2026 | ||
| Global Relocalization | Industrial-like Environment | 24 | Apr 8, 2026 | ||
| Deep research agents / Multi-step reasoning | BrowseComp-Plus OOD | 24 | Apr 8, 2026 | ||
| Multi-hop information-seeking | InfoSeek-Eval ID | 24 | Apr 8, 2026 | ||
| Language Modeling | PubMedQA MdQ | 24 | Apr 7, 2026 | ||
| Long-term Forecasting | Exchange 10% few-shot | 24 | Apr 7, 2026 | ||
| Average Treatment Effect Estimation | IHDP | 24 | Jun 4, 2026 | ||
| Single-transfer cross-chain tracing | Thor25HF Mini | 24 | Apr 7, 2026 | ||
| Multi-hop Question Answering | MuSiQue | 24 | Apr 8, 2026 | ||
| Camera Tracking | DL3DV | 24 | Apr 7, 2026 | ||
| Geolocation | GeoBrowse Level 2 BrowseComp-style | 24 | Apr 7, 2026 | ||
| Geolocation | GeoBrowse Level 1 Visual Cues | 24 | Apr 7, 2026 | ||
| Monocular dynamic-scene reconstruction | HOSNeRF (test) | 24 | Jun 30, 2026 | ||
| Multi-hop Retrieval | MultiHop-RAG (test) | 24 | Apr 7, 2026 | ||
| Bivariate Causal Discovery | SIM-ln | 24 | Apr 8, 2026 |