Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 80 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Object Detection | COCO | 137 | Apr 21, 2026 | ||
| Image Classification | CIFAR-100-C | 137 | Jul 2, 2026 | ||
| RGB-D Salient Object Detection | NJU2K (test) | 137 | Feb 26, 2026 | ||
| Surface Normal Prediction | NYU v2 | 137 | Jun 4, 2026 | ||
| Salient Object Detection | HKU-IS (test) | 137 | Feb 26, 2026 | ||
| Optical Flow | MPI-Sintel final (test) | 137 | Feb 26, 2026 | ||
| Web navigation and task completion | WebArena (test) | 137 | Apr 21, 2026 | ||
| Mathematical Reasoning | Olympiad | 137 | Mar 24, 2026 | ||
| Table Question Answering | TableBench 1.0 (test) | 136 | May 21, 2026 | ||
| Fact Checking | TableBench (test) | 136 | May 21, 2026 | ||
| Performance Estimation | DICES | 136 | Apr 28, 2026 | ||
| Bandwidth Minimization | UF Sparse Matrix Collection (test) | 136 | Apr 23, 2026 | ||
| Logical Reasoning | Formal Logic | 136 | May 27, 2026 | ||
| Mathematical Reasoning | Olympiad | 136 | Jun 9, 2026 | ||
| ECG Classification | PTBXL Super | 136 | Jun 1, 2026 | ||
| AI-generated image detection | Chameleon | 136 | Jul 8, 2026 | ||
| Visual Question Answering | POPE | 136 | Jun 11, 2026 | ||
| Text-based person search | RSTPReid (test) | 136 | Jun 2, 2026 | ||
| No-Reference Image Quality Assessment | TID 2013 | 136 | Jun 30, 2026 | ||
| Video Anomaly Detection | XD-Violence | 136 | Jul 2, 2026 | ||
| Commonsense Reasoning | CommonSenseQA | 136 | Mar 4, 2026 | ||
| No-Reference Image Quality Assessment | SPAQ | 136 | Jun 30, 2026 | ||
| Arithmetic Reasoning | MultiArith (test) | 136 | Jun 26, 2026 | ||
| Super-Resolution | Urban100 x4 | 136 | Jun 19, 2026 | ||
| Video Denoising | Set8 | 136 | Feb 26, 2026 |