Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1122 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Human Preference Prediction | HPD v2 | 25 | May 26, 2026 | ||
| Graph Backdoor Attack | Gossipcop | 25 | Mar 10, 2026 | ||
| Medical Visual Question Answering | SLAKE | 25 | May 22, 2026 | ||
| Logic Reasoning | K&K Logic Puzzles OOD | 25 | Mar 10, 2026 | ||
| Logic Reasoning | K&K Logic Puzzles In-domain | 25 | Mar 10, 2026 | ||
| Machine Unlearning | CIFAR-10 class forgetting (test) | 25 | Mar 10, 2026 | ||
| Machine Unlearning | CIFAR-10 random sampling (test) | 25 | Mar 10, 2026 | ||
| Multi-modal Benchmarking | SEED-Bench | 25 | Mar 10, 2026 | ||
| Retrieval | StanfordCars | 25 | May 19, 2026 | ||
| Chart Question Answering | ChartQAPRO | 25 | Apr 13, 2026 | ||
| Class-Incremental Learning | TinyImageNet Seq | 25 | Apr 23, 2026 | ||
| Dehazing | RESIDE (HSTS) | 25 | May 26, 2026 | ||
| Image Reconstruction | ImageNet 256x256 2012 (test val) | 25 | Mar 9, 2026 | ||
| 3D Referring Expression Segmentation | ScanRefer | 25 | Apr 21, 2026 | ||
| Time Series Anomaly Detection | UCR | 25 | Apr 21, 2026 | ||
| Multi-hop Question Answering | MoreHopQA | 25 | Apr 1, 2026 | ||
| Video Temporal Grounding | ActivityNet | 25 | May 13, 2026 | ||
| Machine Translation | lexical choice benchmark | 25 | Mar 9, 2026 | ||
| Contextual Machine Translation | anaphora benchmark | 25 | Mar 9, 2026 | ||
| Operator Learning | 1D Kuramoto-Sivashinsky ν = 0.075 (test) | 25 | Mar 9, 2026 | ||
| Image Classification | Flowers-102 | 25 | May 20, 2026 | ||
| Link Prediction | CDs | 25 | Jun 11, 2026 | ||
| Infrared Small Target Detection | IRDST-H | 25 | Jun 16, 2026 | ||
| 3D Question Answering | MSQA | 25 | Apr 13, 2026 | ||
| Ad detection | Ad detection New LLMs 1.0 | 25 | Mar 6, 2026 |