Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1711 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Passage Reranking | TREC Deep Learning 2020 | 19 | Apr 21, 2026 | ||
| Passage Reranking | TREC Deep Learning 2019 | 19 | Apr 21, 2026 | ||
| AIGC Video Quality Assessment | T2VQA-DB (test) | 19 | Apr 21, 2026 | ||
| Correlation with human judgments | Flickr8k Expert | 19 | Apr 21, 2026 | ||
| Toxicity Classification | ToxiFrench Sbench | 19 | Apr 21, 2026 | ||
| Transcription | Malvern-Hills dataset (test) | 19 | Apr 21, 2026 | ||
| Handwritten Text Recognition | Malvern-Hills | 19 | Apr 21, 2026 | ||
| Optical Character Recognition | Bentham (test) | 19 | Apr 21, 2026 | ||
| Handwriting Transcription | Bentham dataset | 19 | Apr 21, 2026 | ||
| Parsing | CBRS dataset | 19 | Apr 21, 2026 | ||
| Image Classification | MNIST (Dir(0.5)) | 19 | May 25, 2026 | ||
| Coding | KodCode | 19 | Apr 21, 2026 | ||
| Coding | HumanEval | 19 | Apr 21, 2026 | ||
| TTC forecasting | DAD | 19 | Apr 20, 2026 | ||
| TTC forecasting | DoTA | 19 | Apr 20, 2026 | ||
| Classification | TCGA-NSCLC | 19 | Jun 8, 2026 | ||
| Reasoning | AIME 2025 | 19 | May 1, 2026 | ||
| User simulation | Synthetic Exposure Overall | 19 | Apr 20, 2026 | ||
| User simulation | MIND Real Exposure | 19 | Apr 20, 2026 | ||
| Language Modeling | FineWeb-EDU | 19 | May 12, 2026 | ||
| Passive Sonar Classification | ShipsEar | 19 | Jun 2, 2026 | ||
| Software Engineering / Issue Resolving | SWE-bench Verified | 19 | Apr 28, 2026 | ||
| Perturbation response modelling | Jiang24 | 19 | Apr 16, 2026 | ||
| Potential Outcome Estimation | IBM out-of-sample | 19 | Apr 16, 2026 | ||
| Potential Outcome Estimation | IBM in-sample | 19 | Apr 16, 2026 |