Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2379 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Safety Evaluation | Harmful Prompts | 15 | May 29, 2026 | ||
| AI-Generated Image Detection | GenImage v1.4 (test) | 15 | May 29, 2026 | ||
| Question Answering | NQ | 15 | May 29, 2026 | ||
| Optimal Power Flow (ACOPF) | ACOPF118 (test) | 15 | Jun 4, 2026 | ||
| Mathematical Reasoning | AIME 2025 | 15 | May 29, 2026 | ||
| Materials data quality evaluation | HEA property datasets | 15 | May 29, 2026 | ||
| Object Detection | CARPK | 15 | Jun 30, 2026 | ||
| Audio Deepfake Detection | WaveFake | 15 | Jul 1, 2026 | ||
| Language Modeling | OpenR1-Math | 15 | May 29, 2026 | ||
| Continual Learning | TRACE (overall) | 15 | May 29, 2026 | ||
| Scientific hypothesis discovery | TOMATO-Chem2 (51 top-tier papers) | 15 | May 29, 2026 | ||
| Surgical Rehabilitation Recommendations | Surgical Tasks Dataset | 15 | May 29, 2026 | ||
| Postoperative Risk Prediction | Surgical Tasks Dataset | 15 | May 29, 2026 | ||
| Intraoperative Safety Monitoring | Surgical Tasks Dataset | 15 | May 29, 2026 | ||
| Surgical Planning | Surgical Tasks Dataset | 15 | May 29, 2026 | ||
| Surgical Analysis | Surgical Tasks Dataset | 15 | May 29, 2026 | ||
| Text Reconstruction | BBC News (test) | 15 | May 29, 2026 | ||
| Taxonomic Classification | Marine | 15 | May 29, 2026 | ||
| Taxonomic Classification | Rhizosphere | 15 | May 29, 2026 | ||
| Taxonomic Classification | Urogenital N=57,529 | 15 | May 29, 2026 | ||
| Taxonomic Classification | Oral | 15 | May 29, 2026 | ||
| Taxonomic Classification | Airways | 15 | May 29, 2026 | ||
| Taxonomic Classification | Gastrointestinal | 15 | May 29, 2026 | ||
| Taxonomic classification correction | Marine | 15 | May 29, 2026 | ||
| Taxonomic classification correction | Rhizosphere (N=28,318) | 15 | May 29, 2026 |