Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 211 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Web Shopping Agent | WebShop | 72 | Jul 9, 2026 | ||
| Dynamic Link Prediction | Enron (inductive) | 72 | Jun 4, 2026 | ||
| Tree Explainer Runtime and Stability Analysis | Synthetic data d=100 | 72 | May 8, 2026 | ||
| RAG Leakage Attack | FIQA | 72 | May 8, 2026 | ||
| Multi-Task Instruct-Tuning | SuperNI (test) | 72 | May 8, 2026 | ||
| Tumor Volume Forecasting | Synthetic Cancer Dataset (test) | 72 | Apr 30, 2026 | ||
| Science Reasoning | GPQA | 72 | May 29, 2026 | ||
| Skill Extraction Defense | SkillGuard-5 Evaluation Framework skill-extraction 1.0 (test) | 72 | Apr 24, 2026 | ||
| Jailbreak Attack | Malicious Prompts English (test) | 72 | Apr 24, 2026 | ||
| Machine Unlearning | TOFU 10% forget | 72 | Jun 18, 2026 | ||
| Summarization | FeedSum | 72 | Apr 21, 2026 | ||
| Model Merging | Average of 8 benchmarks | 72 | Apr 21, 2026 | ||
| Jailbreak | JBB-Behaviors utilitarian dilemmas (test) | 72 | Apr 16, 2026 | ||
| Image Classification | CLIP benchmark (test) | 72 | Apr 15, 2026 | ||
| Open-Set Object Detection | Cityscapes → Foggy Cityscapes (val) | 72 | Apr 14, 2026 | ||
| Graduate-level Science Question Answering | GPQA | 72 | Jun 2, 2026 | ||
| Multivariate Time Series Anomaly Detection | SMD | 72 | Jun 23, 2026 | ||
| Causal Discovery | Real-world corpora | 72 | Apr 10, 2026 | ||
| Causal Discovery | iTAG-generated corpora | 72 | Apr 10, 2026 | ||
| Interactive Decision Making | ScienceWorld Seen | 72 | May 19, 2026 | ||
| Vulnerability Analysis | MAVS (test) | 72 | Apr 8, 2026 | ||
| Long-context language modeling | RULER 16K context | 72 | Apr 8, 2026 | ||
| Long-context Reasoning | BABILong 16k | 72 | Apr 8, 2026 | ||
| Reasoning | GSM PRO | 72 | Apr 8, 2026 | ||
| Code Circuit Generation | Code Circuits | 72 | Apr 7, 2026 |