Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1164 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Skilled Forgery Detection | GPDS-S | 24 | Jun 18, 2026 | ||
| Downscaling | WeatherBench ERA5 5.625° to 1.40625° | 24 | Jun 18, 2026 | ||
| Multilingual topic and sentiment classification | SIB-200 and sentiment dataset collection (test) | 24 | Jun 18, 2026 | ||
| Decoder Reconstruction | Gemma 4B IT 3 | 24 | Jun 18, 2026 | ||
| Multitask Language Understanding | MMLU | 24 | Jun 18, 2026 | ||
| Semantic Segmentation | CubiCasa | 24 | Jun 18, 2026 | ||
| World Modelling | AlfWorld | 24 | Jun 17, 2026 | ||
| Countdown | Countdown 5 | 24 | Jun 17, 2026 | ||
| Multi-hop Reasoning | HotpotQA | 24 | Jun 17, 2026 | ||
| Mathematical Reasoning | GSM-Hard | 24 | Jun 17, 2026 | ||
| Mathematical Reasoning | GSM8K | 24 | Jun 17, 2026 | ||
| Success Rate Estimation | RoboMME STOPCUBE | 24 | Jun 17, 2026 | ||
| Causal Discovery | Lorenz-96 D=40, T=1000 | 24 | Jun 17, 2026 | ||
| Video Adversarial Attack | Kinetics-400 | 24 | Jun 17, 2026 | ||
| Video Adversarial Attack | HMDB-51 | 24 | Jun 17, 2026 | ||
| Deep Research Report Generation | DRB | 24 | Jun 16, 2026 | ||
| Open-vocabulary semantic segmentation | Pascal VOC 2012 V20 | 24 | Jun 16, 2026 | ||
| Profession Prediction | Bias-in-Bios (BiB) balanced (test) | 24 | Jun 16, 2026 | ||
| PDE Solving | Heat PDE | 24 | Jun 16, 2026 | ||
| PDE Solving | Diffusion PDE | 24 | Jun 16, 2026 | ||
| Question Answering | CoQA | 24 | Jun 16, 2026 | ||
| Machine Unlearning | FEMNIST natural partition (test) | 24 | Jun 16, 2026 | ||
| Machine Unlearning | CIFAR-100 alpha_dir = 0.5 (test) | 24 | Jun 16, 2026 | ||
| Machine Unlearning | CIFAR-10 alpha_dir = 0.5 (test) | 24 | Jun 16, 2026 | ||
| Clinical temporal classification | UCI-HAR (test) | 24 | Jun 16, 2026 |