Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1116 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| High-level Stance Classification | Woman | 25 | Apr 3, 2026 | ||
| Fine-grained Stance Classification | Woman | 25 | Apr 3, 2026 | ||
| Long-context Memory | LOCOMO | 25 | May 7, 2026 | ||
| Question Answering | BrowseComp-Plus | 25 | May 27, 2026 | ||
| Medical Visual Question Answering | MIMIC-CXR | 25 | Jun 25, 2026 | ||
| Time Series Classification | benchmark datasets 30% Missing (test) | 25 | Apr 3, 2026 | ||
| Time Series Classification | 30 benchmark datasets Regular (test) | 25 | Apr 3, 2026 | ||
| Untargeted identity retrieval attack | VGGFace2 a dslr portrait of sks person prompt | 25 | Apr 2, 2026 | ||
| Untargeted identity retrieval attack | VGGFace2 a photo of sks person prompt | 25 | Apr 2, 2026 | ||
| Code Correctness Evaluation | BCB | 25 | Apr 2, 2026 | ||
| Code Correctness Evaluation | HE-JA | 25 | Apr 2, 2026 | ||
| Code Correctness Evaluation | HE-JS | 25 | Apr 2, 2026 | ||
| Code Correctness Evaluation | HE-Go | 25 | Apr 2, 2026 | ||
| Code Correctness Evaluation | HE-CPP | 25 | Apr 2, 2026 | ||
| Code Correctness Evaluation | HE-PY | 25 | Apr 2, 2026 | ||
| Hair-color classification | CelebA | 25 | Apr 1, 2026 | ||
| Tropical Cyclone track and intensity forecasting | Tropical Cyclone dataset 2020 | 25 | Apr 1, 2026 | ||
| Exact 4-vertex motif counting | Erdős-Rényi graphs G(n, p) synthetic n = 2000 | 25 | Apr 1, 2026 | ||
| Peg Insertion | Real-world | 25 | May 8, 2026 | ||
| Finding target T_uniform | Math | 25 | Mar 31, 2026 | ||
| Finding target T_uniform | MeD | 25 | Mar 31, 2026 | ||
| Long-horizon agentic tasks | BrowseComp-ZH Our Settings | 25 | Mar 31, 2026 | ||
| Topic Modeling | BanFakeNews | 25 | Mar 31, 2026 | ||
| Robot Manipulation | MimicGen | 25 | Jun 30, 2026 | ||
| Novel View Synthesis | H+S scenes | 25 | Mar 31, 2026 |