Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1132 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Topic Classification | Reuters-21578 (test) | 25 | May 7, 2026 | ||
| Mathematical Reasoning | Minerva | 25 | Mar 4, 2026 | ||
| Factual verification and patient-contextual reasoning | MediEval 1.0 (test) | 25 | Feb 26, 2026 | ||
| Android Device Automation | AndroidLab (test) | 25 | Feb 26, 2026 | ||
| inference memory | inference memory | 25 | Feb 26, 2026 | ||
| self-affirmation | MT-Bench-101 | 25 | Feb 26, 2026 | ||
| Medical Diagnosis | agent-CMB | 25 | Feb 26, 2026 | ||
| Medical Diagnosis | MedQA agent | 25 | Feb 26, 2026 | ||
| Readability Style Transfer | CNN/DM (test) | 25 | Feb 26, 2026 | ||
| Question Answering | MMLU (test) | 25 | Mar 16, 2026 | ||
| Long Context | MRCR | 25 | Jun 1, 2026 | ||
| Chinese General Knowledge | CMMLU | 25 | May 15, 2026 | ||
| Graduate-level Science Question Answering | GPQA | 25 | May 13, 2026 | ||
| Visual Math | ChartQA | 25 | Apr 28, 2026 | ||
| Semantic-Acoustic Alignment | SALMon | 25 | Feb 26, 2026 | ||
| Acoustic Consistency | SALMon (continuation) | 25 | Feb 26, 2026 | ||
| Multi-task Performance Evaluation | GPQA-Diamond, GSM8K, MATH-500, AIME’24, and IFEval Aggregate | 25 | Feb 26, 2026 | ||
| Knowledge Graph Construction | MINE benchmark 100 articles | 25 | Feb 26, 2026 | ||
| Knowledge Graph Extraction | MINE benchmark 1.0 (100 articles) (test) | 25 | Feb 26, 2026 | ||
| Factual Retention | MINE | 25 | Feb 26, 2026 | ||
| Factual Correction | CONFLICTS | 25 | Feb 26, 2026 | ||
| Mathematical Reasoning | AMC23 | 25 | May 29, 2026 | ||
| Infilling | ROCStories | 25 | Jul 3, 2026 | ||
| Instruction Following | Tulu3 Evaluation Suite pool (test) | 25 | Feb 26, 2026 | ||
| Text Anomaly Detection | TAD-Liar2 | 25 | Feb 26, 2026 |