Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1746 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Math Reasoning | OlympiadBench | 19 | Feb 26, 2026 | ||
| Pause Handling | Full-Duplex-Bench Candor | 19 | Jun 18, 2026 | ||
| General Knowledge | CEval | 19 | Apr 28, 2026 | ||
| Mathematical Reasoning | GSM8K | 19 | Feb 26, 2026 | ||
| Mathematical Reasoning | MATH500 | 19 | Feb 26, 2026 | ||
| Visual Question Answering | HallusionBench | 19 | Jul 7, 2026 | ||
| Instruction Tuning | Alpaca instruction-tuning 52k | 19 | Feb 26, 2026 | ||
| Code Generation | MBPP | 19 | Feb 26, 2026 | ||
| Design & Synthesis | PolyBench (test) | 19 | Feb 26, 2026 | ||
| Advanced Property Reasoning | PolyBench (test) | 19 | Feb 26, 2026 | ||
| Property Comparison & Ranking | PolyBench (test) | 19 | Feb 26, 2026 | ||
| Property Prediction | PolyBench (test) | 19 | Feb 26, 2026 | ||
| Polymer Concepts | PolyBench 1.0 (test) | 19 | Feb 26, 2026 | ||
| Structural Understanding | PolyBench 1.0 (test) | 19 | Feb 26, 2026 | ||
| Reranking | SciRAG-SSLI hard 1.0 (test) | 19 | Feb 26, 2026 | ||
| Reranking | SciRAG-SSLI easy 1.0 (test) | 19 | Feb 26, 2026 | ||
| Scientific Question Answering | SciRAG-SSLI hard 1.0 (test) | 19 | Feb 26, 2026 | ||
| Scientific Question Answering | SciRAG-SSLI easy 1.0 (test) | 19 | Feb 26, 2026 | ||
| Binary Classification | Bank Marketing | 19 | Feb 26, 2026 | ||
| Binary Classification | Income | 19 | Feb 26, 2026 | ||
| Automatic Speech Recognition | WenetSpeech net | 19 | May 28, 2026 | ||
| Language Modeling | CODEPARROT | 19 | May 14, 2026 | ||
| Scientific Reasoning | GPQA Diamond | 19 | Mar 4, 2026 | ||
| Coreference Resolution | WSC (test) | 19 | Jun 1, 2026 | ||
| Public Health Specialized Reasoning | GlobalHealthAtlas representative subset (test) | 19 | Feb 26, 2026 |