Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2142 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Summarization | arXiv 163w 1,000 samples (test) | 16 | Jun 2, 2026 | ||
| Summarization | PubMed 205w 1,000 samples (test) | 16 | Jun 2, 2026 | ||
| Summarization | CNN/DM 55w 1,000 samples (test) | 16 | Jun 2, 2026 | ||
| Summarization | XSum 21w 1,000 samples (test) | 16 | Jun 2, 2026 | ||
| Summarization | arXiv | 16 | Jun 2, 2026 | ||
| Summarization | PubMed | 16 | Jun 2, 2026 | ||
| Summarization | XSum | 16 | Jun 2, 2026 | ||
| Robot Manipulation | Robosuite Square | 16 | Jun 2, 2026 | ||
| Bias Evaluation (Religion) | BBQ Religion (test) | 16 | Jun 2, 2026 | ||
| Bias Evaluation (Age) | BBQ Age (test) | 16 | Jun 2, 2026 | ||
| Natural Language Processing Reasoning | BBH-NLP (test) | 16 | Jun 2, 2026 | ||
| Algorithmic Reasoning | BBH-Algorithmic (test) | 16 | Jun 2, 2026 | ||
| Language Modeling | FineWeb 10B 8K sequence length | 16 | Jun 2, 2026 | ||
| Language Modeling | FineWeb 10B 4K sequence length | 16 | Jun 2, 2026 | ||
| Language Modeling | FineWeb 10B 2K sequence length | 16 | Jun 2, 2026 | ||
| Language Modeling | FineWeb 10B 1K sequence length | 16 | Jun 2, 2026 | ||
| Plan Generation | Robo Challenge (Online) | 16 | Jun 2, 2026 | ||
| Medical Question Answering | MedQA, MedMCQA, and PubMedQA (Aggregate 1,000 each) | 16 | Jun 2, 2026 | ||
| Robotic Vision-Language Tasks | RoboStressBench | 16 | Jun 2, 2026 | ||
| Image Classification | CIFAR-10 (test) | 16 | Jun 2, 2026 | ||
| Image Classification | CIFAR-100 (test) | 16 | Jun 2, 2026 | ||
| Conformal Prediction | crime | 16 | Jun 2, 2026 | ||
| Conformal Prediction | concrete | 16 | Jun 2, 2026 | ||
| Conformal Prediction | airfoil | 16 | Jun 2, 2026 | ||
| Conformal Prediction | Gaussian | 16 | Jun 2, 2026 |