Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1234 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Clustering | Seeds | 24 | May 22, 2026 | ||
| Question Answering | ARC (test) | 24 | Feb 26, 2026 | ||
| Mathematical Reasoning | GSM8K (test) | 24 | Feb 26, 2026 | ||
| Symbolic Reasoning | Countdown | 24 | Feb 26, 2026 | ||
| Code Generation | HumanEval | 24 | Feb 26, 2026 | ||
| Density Reconstruction | HighD | 24 | Feb 26, 2026 | ||
| Speed Reconstruction | HighD | 24 | Feb 26, 2026 | ||
| Intrusion Detection | UNSW-NB15 | 24 | Jun 30, 2026 | ||
| Image Classification | DomainNet 126 | 24 | May 8, 2026 | ||
| Image-to-Text Retrieval | Flickr30k | 24 | Feb 26, 2026 | ||
| Text-to-Image Retrieval | Flickr30k | 24 | Feb 26, 2026 | ||
| Gröbner basis computation | Polynomial systems over F7 n=13 (test) | 24 | Feb 26, 2026 | ||
| Brain age estimation | IXI (test) | 24 | Feb 26, 2026 | ||
| Operator Learning | Synthetic Dataset | 24 | Feb 26, 2026 | ||
| Inpainting | ImageNet 256x256 (val) | 24 | Jun 30, 2026 | ||
| Counterfactual Explanation | chscase census2 | 24 | May 29, 2026 | ||
| Counterfactual Explanation | glass | 24 | May 29, 2026 | ||
| Counterfactual Explanation | baskball | 24 | May 29, 2026 | ||
| Trust Prediction | Ciao (80%-10%-10%) | 24 | Jun 16, 2026 | ||
| Forecasting | Cash Demand Clean (test) | 24 | Feb 26, 2026 | ||
| Long-sequence time-series forecasting | Electricity | 24 | Feb 26, 2026 | ||
| Long-sequence time-series forecasting | IDEA | 24 | Feb 26, 2026 | ||
| Long-sequence time-series forecasting | Power | 24 | Feb 26, 2026 | ||
| Long-sequence time-series forecasting | Temp. | 24 | Feb 26, 2026 | ||
| Audio Classification | Speech Commands Spectrogram Mini (train) | 24 | Feb 26, 2026 |