Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 413 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Distribution Learning | Uniform distribution rho = 1 | 48 | Feb 26, 2026 | ||
| Distribution Learning | Gaussian distribution rho = 2 (test) | 48 | Feb 26, 2026 | ||
| Data Valuation | MNIST | 48 | May 6, 2026 | ||
| Data Valuation | CIFAR10 | 48 | Feb 26, 2026 | ||
| LLM Decoding | Llama 70B 3.1 | 48 | Feb 26, 2026 | ||
| Citation Prediction Task 2 | CiteRAG 1.0 (test) | 48 | Feb 26, 2026 | ||
| Citation Prediction Task 1 | CiteRAG 1.0 (test) | 48 | Feb 26, 2026 | ||
| Sequential Recommendation | Beauty | 48 | Jun 2, 2026 | ||
| Video Jailbreaking | MM-SafetyBench 1.0 (test) | 48 | Feb 26, 2026 | ||
| Video Jailbreaking | COCO 2017 (test) | 48 | Feb 26, 2026 | ||
| Text-to-image generation | DrawBench | 48 | Mar 4, 2026 | ||
| Document Visual Question Answering | MMLongbench doc | 48 | Apr 27, 2026 | ||
| Logical Reasoning | LogicVista | 48 | Apr 15, 2026 | ||
| Online Video Understanding | OVO-Bench | 48 | Mar 20, 2026 | ||
| Relative Pose and Focal Length Estimation | KITTI (sequences 00-10) | 48 | Feb 26, 2026 | ||
| Image Denoising | HighISO | 48 | Apr 3, 2026 | ||
| Text-to-Image Generation | HPS v3 | 48 | May 26, 2026 | ||
| Few-Shot Segmentation | Polyp | 48 | Feb 26, 2026 | ||
| Autonomous Driving Trajectory Planning | NAVSIM navhard-two-stage v2 (test) | 48 | Jun 8, 2026 | ||
| Medical Visual Question Answering | MicroVQA | 48 | May 12, 2026 | ||
| Dense Video Captioning | ActivityNet Captions | 48 | May 14, 2026 | ||
| Multi-contrast MRI Reconstruction | Brats 2018 (test) | 48 | Feb 26, 2026 | ||
| Few-Shot Classification | AID | 48 | Feb 26, 2026 | ||
| Speech-Preserving Facial Expression Manipulation | MEAD (intra-identity) | 48 | Feb 26, 2026 | ||
| Medical Visual Question Answering | OmniMedVQA | 48 | Jun 1, 2026 |