Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 505 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Inpainting | SD Inpainting 1.5 | 42 | Mar 16, 2026 | ||
| Visual Question Answering | OKVQA | 42 | Mar 16, 2026 | ||
| Visual Question Answering | VQA v2 | 42 | Mar 16, 2026 | ||
| Autonomous Racing | Simulated Racetracks (test) | 42 | Mar 16, 2026 | ||
| Autonomous Racing | Simulated Racetracks (train) | 42 | Mar 16, 2026 | ||
| Math Reasoning | MATH 500 | 42 | Jun 30, 2026 | ||
| Face Generation | FFHQ | 42 | Mar 16, 2026 | ||
| Unconditional generation | LSUN Bedroom 256x256 (test) | 42 | Mar 13, 2026 | ||
| Intrinsic Dimensionality Estimation | 6D sphere (S6) embedded in R11 with Gaussian noise synthetic (test) | 42 | Mar 12, 2026 | ||
| Mathematical Reasoning | AIME 2025 | 42 | Jun 19, 2026 | ||
| Semantic Segmentation | MADOS | 42 | May 28, 2026 | ||
| Federated Open-Set Active Learning | FedEMBED R = 10 (test) | 42 | Mar 10, 2026 | ||
| Federated Open-Set Active Learning | FedISIC R = 5 (test) | 42 | Mar 10, 2026 | ||
| Point map estimation | DTU | 42 | May 18, 2026 | ||
| Semantic Segmentation | Pascal VOC 2012 | 42 | Apr 15, 2026 | ||
| Hardware Vulnerability Detection | RTL Hardware Vulnerability | 42 | Mar 9, 2026 | ||
| Multi-turn Chat Evaluation | MT-Bench | 42 | Jun 11, 2026 | ||
| 3D Semantic Segmentation | ScanNet++ | 42 | Jun 15, 2026 | ||
| Uncertainty Estimation | TruthfulQA | 42 | Jun 11, 2026 | ||
| Language Modeling | Shakespeare's text | 42 | Mar 5, 2026 | ||
| Lesion Grading | AIDPATH-G | 42 | Mar 4, 2026 | ||
| Localization | DSEC (test) | 42 | Mar 4, 2026 | ||
| Super resolution 4x | FFHQ | 42 | May 14, 2026 | ||
| MRI Super-Resolution | IXI | 42 | Jun 26, 2026 | ||
| Color Image Recovery | Sailboat color image | 42 | Mar 4, 2026 |