Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 270 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Uncertainty Quantification | OKVQA | 62 | Jul 1, 2026 | ||
| Jailbreak Attack | SorryBench | 62 | Jun 29, 2026 | ||
| Question Answering | HotpotQA PIA (test) | 62 | May 25, 2026 | ||
| Node Classification | PubMed (test) | 62 | Jun 11, 2026 | ||
| Visual Spatial Reasoning | VSR | 62 | Jun 24, 2026 | ||
| Natural Language Understanding | GLUE | 62 | Jul 7, 2026 | ||
| Open-world Knowledge Graph Question Answering | AskGNN arxiv2023 ogbn-arxiv ogbn-products 1-Hop | 62 | Apr 16, 2026 | ||
| Summarization | CNNDM | 62 | Apr 10, 2026 | ||
| Commonsense Reasoning | HellaSwag | 62 | May 11, 2026 | ||
| Code generation | HumanEval | 62 | Jul 1, 2026 | ||
| Multimodal Jailbreak Attack | HarmBench | 62 | May 27, 2026 | ||
| Text-to-Image Generation | GenEval 2 | 62 | Jul 3, 2026 | ||
| Image Classification | CIFAR-100 Skewed (test) | 62 | Mar 16, 2026 | ||
| Image Super-Resolution | BSD100 | 62 | May 26, 2026 | ||
| Classification | Breast Cancer | 62 | Jul 1, 2026 | ||
| Hallucination Detection | MMLU | 62 | Jun 18, 2026 | ||
| User Churn Prediction | Rel Hm | 62 | May 25, 2026 | ||
| Vision-Language Navigation | RxR (val-unseen) | 62 | May 29, 2026 | ||
| Tool Use and Reasoning | Earth-Bench | 62 | May 14, 2026 | ||
| Anomaly Generation | VisA | 62 | Apr 10, 2026 | ||
| Node classification | DBLP-CA | 62 | May 12, 2026 | ||
| Question Answering | LongBench Qasper | 62 | May 22, 2026 | ||
| Language Modeling | WikiText (val) | 62 | May 26, 2026 | ||
| Classification | IMDB | 62 | Jun 9, 2026 | ||
| Recommendation | Sports | 62 | May 4, 2026 |