Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1070 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Medical Question Answering | CMExam | 26 | Jul 1, 2026 | ||
| Classification | CIFAR-10N | 26 | Jun 4, 2026 | ||
| Code Generation | LiveCodeBench Hard | 26 | May 7, 2026 | ||
| Question Answering | MMLU Professional Law | 26 | Feb 26, 2026 | ||
| Medical Question Answering | MedConceptsQA | 26 | Feb 26, 2026 | ||
| Fraud Detection | T-finance (1% label ratio) | 26 | Jun 29, 2026 | ||
| Emotion Recognition | CH-SIMS 2 | 26 | Feb 26, 2026 | ||
| Emotion Recognition | CH-SIMS | 26 | Feb 26, 2026 | ||
| Emotion Recognition | MOSEI | 26 | Feb 26, 2026 | ||
| Emotion Recognition | MOSI | 26 | Feb 26, 2026 | ||
| Image Classification | CINIC-10 non-iid | 26 | Feb 26, 2026 | ||
| Hierarchical Reasoning | ListOps Long Range Arena (test) | 26 | Feb 26, 2026 | ||
| Node Classification | Ele-fashion | 26 | May 14, 2026 | ||
| Edge Unlearning | Photo hard | 26 | Feb 26, 2026 | ||
| Graph Classification | Ogbn-Products | 26 | Feb 26, 2026 | ||
| Text Generation | MSCOCO | 26 | Feb 26, 2026 | ||
| Mathematical Reasoning | MATH (test) | 26 | Mar 5, 2026 | ||
| Anomaly Detection | ACM | 26 | May 27, 2026 | ||
| Legal Knowledge Evaluation | Legal Domain CaseHOLD, MMLU-L | 26 | Feb 26, 2026 | ||
| Membership Inference Attack | Wikipedia en | 26 | Feb 26, 2026 | ||
| Membership Inference Attack | PubMed Central | 26 | Feb 26, 2026 | ||
| Membership Inference Attack | HackerNews | 26 | Feb 26, 2026 | ||
| Time Series Forecasting | ETTh1 Horizon 96 (test) | 26 | May 19, 2026 | ||
| Math Reasoning | AIME25 | 26 | Apr 2, 2026 | ||
| Math Reasoning | AIME 24 | 26 | Apr 2, 2026 |