Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 221 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Anomaly Detection | Head-CT | 71 | Apr 6, 2026 | ||
| Vision Understanding | MMMU | 71 | Jul 7, 2026 | ||
| Risk measure computation | Sparse random domains smaller scale | 70 | Jul 7, 2026 | ||
| Selective Question Answering | TriviaQA (test) | 70 | Jul 7, 2026 | ||
| Imputation | Superconductivity MNAR | 70 | Jul 7, 2026 | ||
| Robustness Evaluation | Robust LQR | 70 | Jun 4, 2026 | ||
| Robustness Evaluation | Robust LQR adversarial Normalized performance (test) | 70 | Jun 4, 2026 | ||
| Classification | Land Use Fine | 70 | Jun 2, 2026 | ||
| Classification | Land Use Coarse | 70 | Jun 2, 2026 | ||
| Mathematical Reasoning | AIME24 | 70 | Jun 30, 2026 | ||
| Uncertainty Quantification | OKVQA, VizWiz, VQA-RAD, and AdVQA (Average) | 70 | May 27, 2026 | ||
| Role-playing | CharacterBench | 70 | Jun 26, 2026 | ||
| Harmfulness Detection | BeaverTails bottom 30% uncertainty slice (test) | 70 | May 21, 2026 | ||
| Sponsored recommendation evaluation | Sponsored recommendation dataset 1,000-row and 200-row pools | 70 | May 14, 2026 | ||
| Copyright Verification | CIFAR-100 (test) | 70 | May 14, 2026 | ||
| Over-refusal Evaluation | XSTest | 70 | Jul 3, 2026 | ||
| Node Classification | Computer (test) | 70 | Jun 4, 2026 | ||
| Node Classification | PUBMED | 70 | May 8, 2026 | ||
| Node Classification | CORA | 70 | May 8, 2026 | ||
| Classification | Arcene | 70 | Jun 5, 2026 | ||
| General Language Understanding and Reasoning | General Benchmarks MMLU, HellaSwag, OBQA, WinoGrande, ARC-C, PiQA, SciQ, LogiQA | 70 | Apr 14, 2026 | ||
| Text-based Visual Question Answering | TextVQA | 70 | Jun 24, 2026 | ||
| Novel Recommendation | MovieLens | 70 | Apr 10, 2026 | ||
| Question Answering | SQuAD | 70 | Apr 10, 2026 | ||
| Question Answering | NQ | 70 | Apr 10, 2026 |