Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 706 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Program Synthesis | C-RASP Synthesis Benchmark Suite Regular, Counting, and Context-free Languages | 34 | Feb 26, 2026 | ||
| PDE solving | Navier-Stokes 2D | 34 | Jun 11, 2026 | ||
| Model Editing | WikiBigEdit | 34 | May 12, 2026 | ||
| Commonsense Reasoning | HellaSwag 10-shot (test) | 34 | Feb 26, 2026 | ||
| Contextual Privacy Preservation | PrivacyLens (test) | 34 | May 22, 2026 | ||
| Underwater Image Enhancement | EUVP | 34 | Jun 16, 2026 | ||
| Medical Image Segmentation | AMOS (test) | 34 | Apr 6, 2026 | ||
| Speaker Counting | LibriCount | 34 | Jun 26, 2026 | ||
| Audio-based Reasoning | BigBench Audio | 34 | Jul 7, 2026 | ||
| Robotic Manipulation | RoboTwin 2.0 (test) | 34 | Jun 11, 2026 | ||
| Multi-Agent Reinforcement Learning | SMAC | 34 | Jun 18, 2026 | ||
| Probabilistic Time Series Forecasting | ETTm1 | 34 | May 25, 2026 | ||
| Image Classification | RESISC45, SVHN Unseen Tasks (test) | 34 | Feb 26, 2026 | ||
| Image Classification | SUN397, Cars, EuroSAT, GTSRB, MNIST, DTD Seen Tasks (test) | 34 | Feb 26, 2026 | ||
| Maximum Independent Set | Maximum Independent Set Medium (m) | 34 | Mar 26, 2026 | ||
| Image Classification | CINIC-10 iid (test) | 34 | May 15, 2026 | ||
| Node Classification | Physics | 34 | Feb 26, 2026 | ||
| Node Classification | CS | 34 | Jul 3, 2026 | ||
| Sequential Recommendation | Amazon Instruments | 34 | May 20, 2026 | ||
| Question Answering | GPQA | 34 | Mar 10, 2026 | ||
| Storytelling Image Generation | CogBench ISA (test) | 34 | Feb 26, 2026 | ||
| Zero-Shot Classification | SUN | 34 | Jul 7, 2026 | ||
| Generated Image Detection | GenImage v1.4 (test) | 34 | Apr 21, 2026 | ||
| Multi-view Clustering | HandWritten | 34 | Jun 4, 2026 | ||
| Medical Report Generation | MIMIC-CXR | 34 | Jun 5, 2026 |