Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 704 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | Tiny-ImageNet | 34 | Mar 20, 2026 | ||
| Out-of-Distribution Detection | CIFAR-100 | 34 | Mar 20, 2026 | ||
| Mathematical Reasoning | HMMT25 | 34 | Jun 23, 2026 | ||
| Survival Prediction | GBMLGG | 34 | Jun 24, 2026 | ||
| Low-light image enhancement | LOL v1 | 34 | Apr 14, 2026 | ||
| Seizure detection | CHB-MIT | 34 | May 15, 2026 | ||
| Anomaly Detection | ADBench | 34 | Jun 12, 2026 | ||
| Automatic Speech Recognition | LibriSpeech Clean other (test) | 34 | Apr 21, 2026 | ||
| Combined | Multilingual Benchmark | 34 | Mar 13, 2026 | ||
| Spatio-temporal forecasting | CAMS | 34 | Mar 12, 2026 | ||
| Spatio-temporal forecasting | ERA5 | 34 | Mar 12, 2026 | ||
| Reasoning Quality Assessment | Social iqa | 34 | Mar 12, 2026 | ||
| Medical Image Classification | Blood | 34 | Mar 26, 2026 | ||
| Depth Estimation | Cityscapes | 34 | Mar 30, 2026 | ||
| Multi-modal Understanding | MMMU Pro (Overall) | 34 | May 1, 2026 | ||
| Mathematical Visual Question Answering | MathVision | 34 | Apr 10, 2026 | ||
| Visual Question Answering | VQA v2 | 34 | Mar 10, 2026 | ||
| Whole-slide image classification | Camelyon 17 | 34 | May 7, 2026 | ||
| Image Classification | ImageNet 1k 1.0 (val) | 34 | Mar 10, 2026 | ||
| Perturbation-based evaluation | VQA v2 | 34 | Mar 9, 2026 | ||
| Perturbation-based evaluation | ImageNet | 34 | Mar 9, 2026 | ||
| Irregularly Sampled Time Series Forecasting | MIMIC | 34 | Mar 16, 2026 | ||
| Vision-Audio-Text | Omnibench | 34 | Mar 6, 2026 | ||
| Audio-Text | Wenetspeech | 34 | Mar 6, 2026 | ||
| Inductive dynamic link prediction | Social Evo. | 34 | Jun 4, 2026 |