Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2231 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Binary Classification | STL-10 | 16 | Mar 4, 2026 | ||
| Binary Classification | CIFAR-100 | 16 | Mar 4, 2026 | ||
| Binary Classification | CIFAR-10 | 16 | Mar 4, 2026 | ||
| Poisoned Sample Detection | NQ (IID) | 16 | Mar 4, 2026 | ||
| Poisoned Sample Detection | CoQA (IID) | 16 | Mar 4, 2026 | ||
| Poisoned Sample Detection | FreebaseQA (IID) | 16 | Mar 4, 2026 | ||
| Poisoned Sample Detection | WebQA (IID) | 16 | Mar 4, 2026 | ||
| Poisoned sample detection | NQ (NIID-1) | 16 | Mar 4, 2026 | ||
| Poisoned sample detection | CoQA (NIID-1) | 16 | Mar 4, 2026 | ||
| Poisoned sample detection | FreebaseQA NIID-1 | 16 | Mar 4, 2026 | ||
| Poisoned sample detection | WebQA NIID-1 | 16 | Mar 4, 2026 | ||
| Language Modeling | NLP Benchmark Suite Aggregate | 16 | Mar 4, 2026 | ||
| Question Answering | BoolQ | 16 | Mar 4, 2026 | ||
| Algebraic Reasoning | AQuA-RAT | 16 | Mar 4, 2026 | ||
| Commonsense Reasoning | Winogrande | 16 | Mar 4, 2026 | ||
| CT Reconstruction | AAPM Low Dose CT 2016 (test) | 16 | Mar 4, 2026 | ||
| Named Entity Recognition | MIMIC-III | 16 | Mar 4, 2026 | ||
| Video Generation | VBench | 16 | Mar 19, 2026 | ||
| Conformal Prediction | Skin Lesion | 16 | Mar 4, 2026 | ||
| Conformal Prediction | H&E | 16 | Mar 4, 2026 | ||
| Video Generation | Latte 16 frames, 512×512 | 16 | Mar 4, 2026 | ||
| Video Generation | Open-Sora-Plan 221 frames, 512×512 | 16 | Mar 4, 2026 | ||
| Video Generation | Open-Sora 204 frames, 480P | 16 | Mar 4, 2026 | ||
| Question Answering | Reasoning Suite Zero-shot (ArcC, ArcE, PiQA, Wino) | 16 | Mar 4, 2026 | ||
| Multiple-Answer Question Answering | QAMPARI | 16 | Jun 2, 2026 |