Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 300 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Optical Flow | Sintel Final | 59 | Mar 31, 2026 | ||
| Optical Flow | Sintel Clean | 59 | Mar 31, 2026 | ||
| Named Entity Recognition | CrossNER | 59 | May 18, 2026 | ||
| Sex Classification | HCP | 59 | May 29, 2026 | ||
| Image Classification | CIFAR-100 LT Imbalance Ratio 10 (test) | 59 | Feb 26, 2026 | ||
| Segmentation | ADE20K | 59 | Mar 20, 2026 | ||
| Video Question Answering | Perception (test) | 59 | Feb 26, 2026 | ||
| Robot Manipulation | LIBERO | 58 | Jul 7, 2026 | ||
| XAI Fidelity Evaluation | ImageNet vehicles | 58 | Jun 30, 2026 | ||
| Object Localization | ImageNet vehicles | 58 | Jun 30, 2026 | ||
| Training Efficiency Measurement | Llama S=512 on B200 3.1-8B (base variant) | 58 | Jun 23, 2026 | ||
| End-to-end OCR | 200 images (general scene and document images) (test) | 58 | Jun 12, 2026 | ||
| Regression | Urban Perception avg. 6 tasks | 58 | Jun 2, 2026 | ||
| Question Answering | RQA MC | 58 | May 25, 2026 | ||
| Incompressible Navier-Stokes (NS-2D) | VICON (test) | 58 | May 19, 2026 | ||
| Point cloud reconstruction | 7-Scenes | 58 | Jun 18, 2026 | ||
| Language Modeling | C4 | 58 | Jun 2, 2026 | ||
| Time-series forecasting | Traffic | 58 | May 15, 2026 | ||
| Adversarial Jailbreak Attack | Guanaco 7B | 58 | May 12, 2026 | ||
| Adversarial Jailbreak Attack | Vicuna 7B | 58 | May 12, 2026 | ||
| Toxicity Mitigation | Toxicity Mitigation Dataset 1000 trials (test) | 58 | Apr 23, 2026 | ||
| Uncertainty Estimation | CoQA | 58 | May 8, 2026 | ||
| Continual Unlearning | CIFAR-100 | 58 | May 19, 2026 | ||
| Machine Unlearning | CIFAR-100 10 classes | 58 | Jun 17, 2026 | ||
| Image Classification | SVHN | 58 | May 28, 2026 |