Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1737 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Graph-level Cycle Counting | Chordal Cycle Counting (test) | 19 | May 8, 2026 | ||
| Anomaly Detection | PubMed | 19 | May 20, 2026 | ||
| Automated Software Engineering | SWE-bench Lite | 19 | Feb 26, 2026 | ||
| Graph Anomaly Detection | DGraph-Fin | 19 | Mar 10, 2026 | ||
| Graph Anomaly Detection | ACM | 19 | Feb 26, 2026 | ||
| Graph Anomaly Detection | Citeseer | 19 | Feb 26, 2026 | ||
| Graph Anomaly Detection | Amazon v1 (full) | 19 | Feb 26, 2026 | ||
| Time Series Reasoning | TSUR Reasoning (test) | 19 | Feb 26, 2026 | ||
| Clustering | MNIST | 19 | Feb 26, 2026 | ||
| Counterfactual explanations | Loan-Decision | 19 | Feb 26, 2026 | ||
| Anomaly Detection | Hepatitis | 19 | Mar 17, 2026 | ||
| Offline Reinforcement Learning | Hopper expert | 19 | Feb 26, 2026 | ||
| Zero-shot Downstream Reasoning and Knowledge Tasks | Downstream Reasoning Task Suite (ARC-E, ARC-C, HS, OBQA, PIQA, WG, Arith.) zero-shot | 19 | Feb 26, 2026 | ||
| Language Modeling | Language Modeling Corpus (val) | 19 | Feb 26, 2026 | ||
| Long-context retrieval | RULER 64K context | 19 | Apr 28, 2026 | ||
| Locomotion | D4RL MuJoCo hopper-medium-replay v2 | 19 | May 19, 2026 | ||
| Coding | CRUXEval-O | 19 | May 26, 2026 | ||
| Text Classification | IMDB (test) | 19 | Jul 9, 2026 | ||
| Out-of-Distribution Detection | MNIST (In) FashionMNIST (Out) (test) | 19 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | CIFAR-10 OpenOOD (test) | 19 | May 28, 2026 | ||
| Language Modeling | WikiText-103 (train) | 19 | Jun 1, 2026 | ||
| Mathematical Reasoning | AMC 2023 | 19 | Apr 14, 2026 | ||
| Hierarchical Clustering | birds | 19 | Feb 26, 2026 | ||
| Hierarchical Clustering | mnist | 19 | Feb 26, 2026 | ||
| Information-seeking | BrowseComp | 19 | Feb 26, 2026 |