Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1127 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Circuit Optimization | Two-stage circuit | 25 | Feb 26, 2026 | ||
| Continual Learning | MNIST Split | 25 | Jun 23, 2026 | ||
| Reconstruction | Transfer Learning Few-shot | 25 | Feb 26, 2026 | ||
| Expert-level Question Answering | GPQA | 25 | May 12, 2026 | ||
| Commonsense Reasoning | ARC-e, ARC-c, PIQA, WinoG., HellaS. | 25 | Jun 30, 2026 | ||
| Language Modeling | C4 LLaMA-60M (val) | 25 | May 14, 2026 | ||
| Multi-Task Agent Generalization | Five Agent Environments Average (test) | 25 | Feb 26, 2026 | ||
| Game Solving | Wordle (test) | 25 | Feb 26, 2026 | ||
| Maze Navigation | Maze (test) | 25 | Feb 26, 2026 | ||
| LLM Agent Navigation | BabyAI (test) | 25 | Feb 26, 2026 | ||
| Multi-horizon clinical forecasting | SBP | 25 | Feb 26, 2026 | ||
| Multi-horizon clinical forecasting | MBP | 25 | Feb 26, 2026 | ||
| Multi-horizon clinical forecasting | PEDAP | 25 | Feb 26, 2026 | ||
| Multi-horizon clinical forecasting | DCLP3 | 25 | Feb 26, 2026 | ||
| Deblurring | ImageNet 256 | 25 | May 12, 2026 | ||
| Adversarial Detection | CIFAR-10 | 25 | Jun 29, 2026 | ||
| Zero-shot Question Answering | AveQA | 25 | Feb 26, 2026 | ||
| Image Classification | MNIST iid (10 classes/client) CONV4, 50 rounds (test) | 25 | Feb 26, 2026 | ||
| Time Series Forecasting | ETTh2 | 25 | Feb 26, 2026 | ||
| Edge Unlearning | Chameleon (hard) | 25 | Feb 26, 2026 | ||
| Graph Classification | IMDB-MULTI (IMDB-M) 1.0 (test) | 25 | Feb 26, 2026 | ||
| Graph Classification | IMDB-BINARY 1.0 (test) | 25 | Feb 26, 2026 | ||
| Graph Classification | ENZYMES 1.0 (test) | 25 | Feb 26, 2026 | ||
| Circle Packing | Circle Packing (n=26) | 25 | Jun 18, 2026 | ||
| Node Classification | PubMed | 25 | May 29, 2026 |