Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1191 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-label classification | RCV subset2 | 24 | May 12, 2026 | ||
| Multi-label classification | RCV subset1 | 24 | May 12, 2026 | ||
| Multi-label classification | scene | 24 | May 12, 2026 | ||
| Multi-label classification | birds | 24 | May 12, 2026 | ||
| 48-hour In-Hospital Mortality (48-IHM) | MIMIC IV | 24 | Jun 5, 2026 | ||
| Mathematical Reasoning | MathQA OOD (test) | 24 | May 12, 2026 | ||
| Continual Learning | Curriculum Coding -> Math -> Medical | 24 | May 12, 2026 | ||
| Coding Reasoning | LiveCodeBench 2024.10-2025.02 | 24 | May 12, 2026 | ||
| Reasoning | LiveCodeBench (LCB) 2024.10-2025.02 | 24 | May 12, 2026 | ||
| Reasoning | MMLU-Pro | 24 | May 12, 2026 | ||
| Reasoning | AIME 2025 | 24 | May 12, 2026 | ||
| Reasoning | AIME 2024 | 24 | May 12, 2026 | ||
| Classification | CIFAR-100 | 24 | Jul 2, 2026 | ||
| Selective Classification | Mixture distribution even mixture of seven covariate shifts | 24 | May 12, 2026 | ||
| Selective Classification | JPEG shift | 24 | May 12, 2026 | ||
| Selective Classification | FGSM shift | 24 | May 12, 2026 | ||
| Selective Classification | Low Res. shift | 24 | May 12, 2026 | ||
| Selective Classification | Blur shift | 24 | May 12, 2026 | ||
| Class Unlearning | CIFAR-10 | 24 | May 12, 2026 | ||
| Sample Unlearning | CIFAR-10 | 24 | May 12, 2026 | ||
| Node Classification | OGB-arxiv | 24 | May 12, 2026 | ||
| Node Classification | PubMed | 24 | May 12, 2026 | ||
| Node Classification | Cora | 24 | May 12, 2026 | ||
| Dose-Response Estimation | Synthetic low-dimensional dose-response benchmark asymmetric proxy informativeness | 24 | May 12, 2026 | ||
| Mathematical Reasoning | Avg. (held out) | 24 | May 11, 2026 |