Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1436 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Semantic Similarity | SICK | 21 | May 29, 2026 | ||
| Multimodal Knowledge Editing | FGVEdit | 21 | May 29, 2026 | ||
| Visual Question Answering | GQA | 21 | Jul 2, 2026 | ||
| Summarization | CNN/DM | 21 | May 29, 2026 | ||
| Response Harmfulness Detection | Response Harmfulness Detection Benchmarks (HarmBench, SafeRLHF, BeaverTails, XSTest, WildGuard) | 21 | May 29, 2026 | ||
| Geometric Optimization | MMD | 21 | May 29, 2026 | ||
| Geometric Optimization | CP | 21 | May 29, 2026 | ||
| Open-ended Generation | LLaVA-Bench | 21 | May 29, 2026 | ||
| Recommendation | AL-GR released (test) | 21 | May 29, 2026 | ||
| Abstractive Summarization | CNN/DailyMail (test) | 21 | Jun 5, 2026 | ||
| Online Class-Incremental Learning | ImageNet-100 10 tasks (test) | 21 | May 29, 2026 | ||
| Mathematical Reasoning | HMMT25 | 21 | May 28, 2026 | ||
| Mathematical Reasoning | AIME 25 | 21 | May 28, 2026 | ||
| Mathematical Reasoning | AIME 24 | 21 | May 28, 2026 | ||
| Mathematical and Physics Reasoning | OLYMPIADBENCH | 21 | May 28, 2026 | ||
| Planning | NATURALPLAN | 21 | May 28, 2026 | ||
| Anomaly Localization | VisA | 21 | May 28, 2026 | ||
| Anomaly Detection | MVTec-AD | 21 | May 28, 2026 | ||
| Super-Resolution | OpenSARShip (test) | 21 | May 28, 2026 | ||
| Visual Question Answering | TextVQA | 21 | Jul 7, 2026 | ||
| Image Manipulation Localization | MagicBrush | 21 | Jun 2, 2026 | ||
| Long-context text understanding | LongBench-Pro | 21 | May 28, 2026 | ||
| Forecasting | Forecasting (test) | 21 | May 28, 2026 | ||
| Object-goal navigation | HM3D v2 | 21 | Jun 4, 2026 | ||
| Conditional Average Treatment Effect Estimation | Linear design N1=500 | 21 | May 28, 2026 |