Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1589 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Zero-shot Classification | COCO-80 | 20 | Mar 31, 2026 | ||
| Deep Search | xBench DeepSearch DS-2505 | 20 | Mar 31, 2026 | ||
| Super-resolution | CelebA-HQ (100 images) | 20 | Mar 31, 2026 | ||
| Super-resolution | CelebA (100 images) | 20 | Mar 31, 2026 | ||
| LLM-as-a-judge | ARENA | 20 | Mar 31, 2026 | ||
| LLM-as-a-judge | PRISM | 20 | Mar 31, 2026 | ||
| Multi-Image Question Answering | Molmo QA Benchmarks Multi-Image 19 | 20 | Mar 31, 2026 | ||
| Image Question Answering | Molmo QA Benchmarks Image 19 | 20 | Mar 31, 2026 | ||
| Visual Localization | CV-RHO within-dataset evaluation | 20 | Mar 31, 2026 | ||
| Image Classification | MedMNIST 2D OrganAMNIST | 20 | Mar 31, 2026 | ||
| Edge Detection | BSDS500 (test) | 20 | Mar 31, 2026 | ||
| Continual Learning | CoIN | 20 | Apr 10, 2026 | ||
| Anomaly Detection | Annthyroid | 20 | Jun 30, 2026 | ||
| SLAM | Hilti 2022 | 20 | Jun 25, 2026 | ||
| Drowsiness Estimation | FatigueView | 20 | Apr 10, 2026 | ||
| Question Answering | TriviaQA | 20 | Mar 31, 2026 | ||
| Traveling Salesperson Problem | Synthetic COP instances | 20 | Mar 31, 2026 | ||
| Graduate-level Science QA | GPQA Main | 20 | Jun 30, 2026 | ||
| Human Recognition | LTCC Long-Term Cloth-Changing (test) | 20 | Mar 31, 2026 | ||
| Box Detection | SA-Co | 20 | Mar 31, 2026 | ||
| Image Classification | CIFAR-100 (test) | 20 | Mar 30, 2026 | ||
| Image Classification | CIFAR-10 (test) | 20 | Mar 30, 2026 | ||
| Image Classification | CIFAR-10 (test) | 20 | Mar 30, 2026 | ||
| Activation Steering | ASR Evaluation Set | 20 | Mar 30, 2026 | ||
| Language Modeling | Model-generated outputs | 20 | Mar 30, 2026 |