Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 593 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Time Series Anomaly Detection | PSM | 38 | Mar 30, 2026 | ||
| General Reasoning | GPQA | 38 | Jun 1, 2026 | ||
| Mathematical Reasoning | AIME25 | 38 | May 22, 2026 | ||
| Visual Object Tracking | OTB-100 | 38 | Jul 3, 2026 | ||
| Response correctness and completeness evaluation | Wikipedia | 38 | Feb 26, 2026 | ||
| Molecular Docking Score Optimization | Target proteins (PARP1, FA7, 5HT1B, BRAF, JAK2) (novel top 5% molecules) | 38 | May 12, 2026 | ||
| Code Generation | MBPP | 38 | Feb 27, 2026 | ||
| Deductive Reasoning | ProntoQA | 38 | Apr 23, 2026 | ||
| Summarization | LongBench GovReport | 38 | May 22, 2026 | ||
| Deep Search | Browse Comp | 38 | Mar 31, 2026 | ||
| Node Classification | Arxiv 2023 (test) | 38 | Jun 11, 2026 | ||
| Membership Inference Attack | TUH-EEG Record-level (test) | 38 | Feb 26, 2026 | ||
| Text-to-Image Generation | HPD | 38 | May 27, 2026 | ||
| Low-Rank Matrix Optimization | Molecular Conformation (PDB) | 38 | Feb 26, 2026 | ||
| Automatic Speech Recognition | SEAME SGE (dev) | 38 | Jul 7, 2026 | ||
| Automatic Speech Recognition | SEAME Man (dev) | 38 | Jul 7, 2026 | ||
| Speaker Verification | Vox-H VoxCeleb2 (test) | 38 | Apr 29, 2026 | ||
| Speaker Verification | VoxCeleb2 O (test) | 38 | Apr 29, 2026 | ||
| Audio Deepfake Detection | ASVspoof LA 2019 | 38 | May 19, 2026 | ||
| Neural Architecture Search | NASBench-201 ImageNet16-120 | 38 | Feb 26, 2026 | ||
| Concept Attribution | GoEmotions v1.0 (test) | 38 | Feb 26, 2026 | ||
| Multimodal Reasoning | MATH-Vision (full) | 38 | May 28, 2026 | ||
| Targeted Attack | ImageNet (test) | 38 | Feb 26, 2026 | ||
| PDE Solving | Pipe Structured Mesh (test) | 38 | May 12, 2026 | ||
| PDE Solving | Airfoil Structured Mesh (test) | 38 | May 12, 2026 |