Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1290 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Theorem Proving | MATH 500 | 23 | Jun 30, 2026 | ||
| Incremental Object Detection | PASCAL VOC 2007 (15+5) | 23 | Jul 7, 2026 | ||
| Multimodal Search | MMSearch (test) | 23 | Jun 16, 2026 | ||
| Learner Correctness Simulation | DBE-KT22 | 23 | Jun 16, 2026 | ||
| Complete matched replay suite | ChemLex Acid–Amine Wetlab (complete matched replay suite) | 23 | Jun 15, 2026 | ||
| Chemical Reaction Optimization | Minerva Olympus Suzuki Coupling i (complete matched replay suite) | 23 | Jun 15, 2026 | ||
| 6D Object Pose Estimation | HB | 23 | Jun 15, 2026 | ||
| Combinatorial Optimization | ACS | 23 | Jun 15, 2026 | ||
| Static Path Planning | Sparse Map (C9-C12) | 23 | Jun 15, 2026 | ||
| Static Path Planning | Large Map (C5-C8) | 23 | Jun 15, 2026 | ||
| Static Path Planning | Short Map (C1-C4) | 23 | Jun 15, 2026 | ||
| ASR Correction | RAMC-Corr (test) | 23 | Jun 12, 2026 | ||
| Vulnerability Discovery | Magma | 23 | Jun 12, 2026 | ||
| Software Engineering | SWE-Bench Lite | 23 | Jun 12, 2026 | ||
| Deep Search | BrowseComp v1.0 (test) | 23 | Jun 11, 2026 | ||
| Depression level estimation | DAIC-WOZ (test) | 23 | Jun 11, 2026 | ||
| AI-Generated Image Detection | Average Post-processed | 23 | Jun 11, 2026 | ||
| Diverse Generation | Poetry Foundation | 23 | Jun 11, 2026 | ||
| Diverse Generation | IBM ArgKP | 23 | Jun 11, 2026 | ||
| Chat Generation | Infinite Chats | 23 | Jun 11, 2026 | ||
| Creative Writing Generation | WritingPrompts | 23 | Jun 11, 2026 | ||
| Code Generation | MBPP+ | 23 | Jul 7, 2026 | ||
| Graduate-level STEM Reasoning | GPQA Diamond | 23 | Jun 15, 2026 | ||
| Tabular Regression | Diamonds | 23 | Jun 9, 2026 | ||
| Tabular Classification | OK | 23 | Jun 9, 2026 |