Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1838 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Shot Transition Detection | Public Data | 18 | May 1, 2026 | ||
| Uncertainty Estimation | CommonsenseQA | 18 | May 1, 2026 | ||
| Uncertainty Estimation | SciQ | 18 | May 1, 2026 | ||
| Uncertainty Estimation | SQW (SearchQA) | 18 | May 1, 2026 | ||
| Long-form Text Generation | LongWriter | 18 | May 11, 2026 | ||
| Node Classification | IEEE-CIS-G | 18 | May 1, 2026 | ||
| Hyperspectral Image Super-Resolution | Pavia Centre (test) | 18 | May 1, 2026 | ||
| Hyperspectral Image Super-Resolution | Chikusei 512x512x128 cubes (test) | 18 | May 1, 2026 | ||
| Knowledge Recovery | EntityQuestions (test) | 18 | Apr 30, 2026 | ||
| Long-term forecasting | ETTh1 standard (test) | 18 | Jun 11, 2026 | ||
| Mathematical Reasoning | Mathematical Reasoning Suite (Math500, Gaokao En, Olympiad, GSM8K, AMC23, AIME25, AIME24) | 18 | Apr 30, 2026 | ||
| Document Reranking | MS MARCO Document DL19 | 18 | Apr 30, 2026 | ||
| Voice Anonymization | IEMOCAP (test) | 18 | Apr 30, 2026 | ||
| Voice Anonymization | IEMOCAP (dev) | 18 | Apr 30, 2026 | ||
| Voice Anonymization | LibriSpeech (test) | 18 | Apr 30, 2026 | ||
| Voice Anonymization | LibriSpeech (dev) | 18 | Apr 30, 2026 | ||
| Offline Data-driven Multi-Objective Optimization | DTLZ1, DTLZ2, DTLZ3, DTLZ4, DTLZ5, DTLZ6, DTLZ7, and Omnitest unconstrained benchmarks | 18 | Apr 30, 2026 | ||
| Thresholded classification | TriviaQA | 18 | Apr 30, 2026 | ||
| Thresholded classification | HotpotQA | 18 | Apr 30, 2026 | ||
| Mathematical Problem Solving | AIME 2026 | 18 | Jul 7, 2026 | ||
| Recommendation | Amazon Electronics | 18 | Apr 29, 2026 | ||
| Image Classification | ImageNet | 18 | Apr 29, 2026 | ||
| Speaker Verification | Vox1-O Noise (test) | 18 | Apr 29, 2026 | ||
| Scientific Reasoning | GPQA Diamond | 18 | Apr 29, 2026 | ||
| Mathematical Reasoning | MATH-500 | 18 | Apr 29, 2026 |