Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 302 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Sequential Recommendation | Beauty | 58 | Apr 3, 2026 | ||
| Virtual Try-On | VITON-HD paired | 58 | Jul 1, 2026 | ||
| Text-to-Image Generation | T2I-CompBench | 58 | Jun 23, 2026 | ||
| Conditional Image Generation | ImageNet 256x256 | 58 | Jun 19, 2026 | ||
| Action Recognition | SS Full v2 | 58 | Mar 30, 2026 | ||
| Monte Carlo Denoising | SBMC 1.0 (test) | 58 | Feb 26, 2026 | ||
| Image Classification | Flowers102 | 58 | May 26, 2026 | ||
| Membership Inference Attack | Asclepius (fine-tuned) | 58 | Feb 26, 2026 | ||
| Mathematical Reasoning | MathVerse Vision Only | 58 | Jun 19, 2026 | ||
| Calibration | MMLU | 58 | Jun 11, 2026 | ||
| Generation | SQuAD | 58 | Jun 5, 2026 | ||
| Multi-Hop Question Answering | MuSiQue | 58 | Apr 10, 2026 | ||
| Text-to-SQL | LogicCat | 58 | Feb 26, 2026 | ||
| Age prediction | CHILDES (child-grouped 5-fold CV) | 58 | Feb 26, 2026 | ||
| Language Modeling | FineWeb-Edu (test) | 58 | Jun 2, 2026 | ||
| Name Extraction | BPMN Diagrams (test) | 58 | Feb 26, 2026 | ||
| Table Question Answering | AIT-QA | 58 | Apr 13, 2026 | ||
| Long-context document understanding | MMLongBench-Doc | 58 | Apr 16, 2026 | ||
| Pre-training | C4 (val) | 58 | Apr 13, 2026 | ||
| Object Detection | ExDark | 58 | Apr 14, 2026 | ||
| Multivariate Time Series Anomaly Detection | WADI | 58 | Jun 18, 2026 | ||
| Jailbreak Defense | DeepInception | 58 | Feb 26, 2026 | ||
| Visual Question Answering | MMBench English | 58 | Jul 9, 2026 | ||
| Protein function prediction | PPI (test) | 58 | Jun 9, 2026 | ||
| Face Anti-Spoofing | MSU-MFSD M (test) | 58 | Jul 3, 2026 |