Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1454 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Poisoning Unlearning | CIFAR-10 | 21 | Apr 14, 2026 | ||
| Human Pose Estimation | ExLPose LL-E (test) | 21 | Apr 14, 2026 | ||
| Human Pose Estimation | ExLPose LL-N (test) | 21 | Apr 14, 2026 | ||
| Low-Light Image Enhancement | NPE | 21 | Jun 23, 2026 | ||
| Low-Light Image Enhancement | DICM | 21 | Jun 23, 2026 | ||
| Low-Light Image Enhancement | LIME | 21 | Jun 23, 2026 | ||
| Low-Light Image Enhancement | MEF | 21 | Jun 23, 2026 | ||
| Expressive Evaluation | HRS benchmark | 21 | Apr 14, 2026 | ||
| Infrared Small Target Detection | SIRST-UAVB | 21 | Apr 14, 2026 | ||
| Multiple-choice question answering | 2,000 questions dataset | 21 | Apr 14, 2026 | ||
| Calibration | stream 2,000-question | 21 | Apr 14, 2026 | ||
| Classification with expert deferral | CIFAR-10 redundant expert suite (val) | 21 | Apr 13, 2026 | ||
| Learning to Defer | CIFAR-10 with redundant synthetic experts | 21 | Apr 13, 2026 | ||
| Image Classification Unlearning | CIFAR-10 50% Random Forgetting | 21 | May 18, 2026 | ||
| Image Classification Unlearning | CIFAR-100 50% random data forgetting | 21 | May 18, 2026 | ||
| Robot Manipulation | LIBERO Goal | 21 | Apr 13, 2026 | ||
| Robot Manipulation | LIBERO Spatial | 21 | Apr 13, 2026 | ||
| Partial Multi-label Learning | medical | 21 | Apr 13, 2026 | ||
| Partial Multi-Label Learning | corel5k | 21 | Apr 13, 2026 | ||
| Partial Multi-Label Learning | medical | 21 | Apr 13, 2026 | ||
| Reasoning | GPQA | 21 | May 12, 2026 | ||
| Deepfake Detection | CDF v1 (test) | 21 | Apr 13, 2026 | ||
| Multimodal Hallucination Assessment | HallusionBench | 21 | May 19, 2026 | ||
| Question Answering | MedicalQA | 21 | Jun 4, 2026 | ||
| Machine Unlearning | Tiny-ImageNet 20 classes (forget) | 21 | Apr 10, 2026 |