Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2240 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question Answering | EntityQuestions Frequent | 16 | Feb 26, 2026 | ||
| Question Answering | EntityQuestions (Infrequent) | 16 | Feb 26, 2026 | ||
| Question Answering | EntityQuestions (Long-tail) | 16 | Feb 26, 2026 | ||
| Question Answering | PopQA (Frequent) | 16 | Feb 26, 2026 | ||
| Question Answering | PopQA Infrequent | 16 | Feb 26, 2026 | ||
| Multimodal Understanding | AI2D | 16 | Mar 27, 2026 | ||
| Camera Localization | StereoMIS Average | 16 | Feb 26, 2026 | ||
| Camera Localization | StereoMIS (P2-4) | 16 | Feb 26, 2026 | ||
| Camera Localization | StereoMIS (P2-3) | 16 | Feb 26, 2026 | ||
| Camera Localization | StereoMIS (P2-2) | 16 | Feb 26, 2026 | ||
| Classification | Chaoyang | 16 | Feb 26, 2026 | ||
| Classification | MiceBone | 16 | Feb 26, 2026 | ||
| Latent space generation | Vorticity and Convection Physical Simulation | 16 | Feb 26, 2026 | ||
| Knowledge Graph Retrieval | STaRK-Prime 1.0 (Human) | 16 | Feb 26, 2026 | ||
| Retrieval | STaRK PRIME Human | 16 | Feb 26, 2026 | ||
| Retrieval | STaRK MAG Human | 16 | Feb 26, 2026 | ||
| Retrieval | STaRK AMAZON (Human) | 16 | Feb 26, 2026 | ||
| Stereo Depth Estimation | SQUID zero-shot | 16 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME25 | 16 | Feb 26, 2026 | ||
| PPA Estimation | EDA Designs jpeg, nova, netcard, tate_pairing, CA53, ariane-133 | 16 | Feb 27, 2026 | ||
| Voting behavior prediction | European Parliament Voting Proposals | 16 | Feb 26, 2026 | ||
| Continual Clustering | Texture | 16 | May 12, 2026 | ||
| Continual Clustering | Semeion | 16 | May 12, 2026 | ||
| Continual Clustering | Iris | 16 | May 12, 2026 | ||
| HalfCheetah | Mujoco | 16 | Feb 26, 2026 |