Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 507 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Planning | NavSim (Navhard) | 42 | Jul 9, 2026 | ||
| Unconditional Image Generation | CIFAR-10 32x32 unconditional (test) | 42 | Jul 1, 2026 | ||
| Thematic fit estimation | Fer-Ins | 42 | Feb 26, 2026 | ||
| Thematic fit estimation | Fer-Loc | 42 | Feb 26, 2026 | ||
| Multiple-choice Question Answering | MedMCQA | 42 | May 12, 2026 | ||
| MT-Bench | UltraFeedback | 42 | Feb 26, 2026 | ||
| AlpacaEval 2.0 | UltraFeedback | 42 | Feb 26, 2026 | ||
| Backdoor Certification | CIFAR-10 (test) | 42 | Feb 26, 2026 | ||
| Knowledge Graph Completion | MKG-Y | 42 | Apr 20, 2026 | ||
| Knowledge Graph Completion | MKG-W | 42 | Apr 20, 2026 | ||
| Knowledge Graph Completion | DB15K | 42 | Apr 20, 2026 | ||
| Question Answering | NQ | 42 | Jun 12, 2026 | ||
| Language Modeling | Wikitext-103 | 42 | Feb 26, 2026 | ||
| Disease Diagnosis | ACL Sprain Diagnosis | 42 | Feb 26, 2026 | ||
| Disease Diagnosis | Cartilage Thickness Loss (test) | 42 | Feb 26, 2026 | ||
| Coding | Coding Tasks (test) | 42 | Feb 26, 2026 | ||
| Deep Search | Deep Search Tasks (test) | 42 | Feb 26, 2026 | ||
| Question Answering | MultiExpertQA-P Base and Fine-tuned (FT) | 42 | Feb 26, 2026 | ||
| Long-Term Time Series Forecasting | WTH | 42 | May 19, 2026 | ||
| Bias Discovery | Female-biased prompts | 42 | Feb 26, 2026 | ||
| Web-based Agent Interaction | WebShop (test) | 42 | Apr 14, 2026 | ||
| Image Generation | CIFAR-10 (test) | 42 | May 18, 2026 | ||
| HOMO-LUMO gap prediction | 2D Materials Defect Dataset (10-fold splits) | 42 | Feb 26, 2026 | ||
| Formation energy per site prediction | 2D Materials Defect Dataset (10-fold splits) | 42 | Feb 26, 2026 | ||
| Precipitation Nowcasting | MeteoNet | 42 | Jun 1, 2026 |