Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2198 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Knowledge Graph Completion | Warden Alert (Inductive) | 16 | Apr 6, 2026 | ||
| Physical Plausibility Evaluation | VideoPhy | 16 | Apr 6, 2026 | ||
| Chart Question Answering | ChartX | 16 | Apr 6, 2026 | ||
| 3D Scene Understanding | ScanRefer, Multi3DRefer, Scan2Cap, ScanQA, SQA3D | 16 | Apr 6, 2026 | ||
| Visual Question Answering | ScanQA | 16 | Apr 6, 2026 | ||
| Position State Estimation | nuScenes (test) | 16 | Apr 6, 2026 | ||
| Image Denoising | BSDS 500 (test) | 16 | May 19, 2026 | ||
| Counterfactual Generation | AVICI (test) | 16 | Apr 6, 2026 | ||
| Interventional Generation | AVICI In-distribution | 16 | Apr 6, 2026 | ||
| Sample Generation | AVICI RFF (Out-of-distribution) | 16 | Apr 6, 2026 | ||
| Sample Generation | AVICI LIN (Out-of-distribution) | 16 | Apr 6, 2026 | ||
| Sample Generation | AVICI RFF (In-distribution) | 16 | Apr 6, 2026 | ||
| Sample Generation | AVICI LIN (In-distribution) | 16 | Apr 6, 2026 | ||
| Noise Prediction | AVICI In-distribution | 16 | Apr 6, 2026 | ||
| Traveling Salesperson Problem | TSP-100 (test) | 16 | May 19, 2026 | ||
| Question Answering | AmbigNQ | 16 | Apr 3, 2026 | ||
| Text Embedding | MTEB Multilingual V2 (test) | 16 | Apr 21, 2026 | ||
| LLM-generated text detection | DetectRL Out-of-Domain Multi-LLM 1.0 (test) | 16 | Apr 3, 2026 | ||
| LGT Detection | Mix8 | 16 | Apr 3, 2026 | ||
| Deep search QA | Frames | 16 | Jul 1, 2026 | ||
| Multi-Paper Question Answering | ScholarQABench Multi | 16 | Apr 3, 2026 | ||
| 3-month mortality prediction | French HF dataset | 16 | Apr 3, 2026 | ||
| Novel View Synthesis | Mip-NeRF 360 (Indoor) | 16 | Jun 30, 2026 | ||
| Mid-sagittal plane positioning | Mid-sagittal plane scans | 16 | Apr 3, 2026 | ||
| Video Object Removal | Scene-Bench | 16 | Apr 3, 2026 |