Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 99 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Novel View Synthesis | DTU (test) | 119 | Jul 7, 2026 | ||
| 3D Human Pose and Shape Estimation | Human3.6M (test) | 119 | Feb 26, 2026 | ||
| Temporal Action Segmentation | Breakfast | 119 | Jun 11, 2026 | ||
| Out-of-distribution Detection | CIFAR-10 vs CIFAR-100 (test) | 119 | Jun 30, 2026 | ||
| Text Classification | AgNews | 119 | Feb 26, 2026 | ||
| Graph Classification | NCI1 (10-fold cross-validation) | 119 | Jun 11, 2026 | ||
| Language Understanding | MMLU 0-shot | 119 | Jun 1, 2026 | ||
| Action Recognition | NTU-60 48/12 split | 119 | Apr 21, 2026 | ||
| Commonsense Reasoning | StrategyQA (test) | 119 | May 29, 2026 | ||
| Robotic Manipulation | LIBERO v1 (test) | 118 | Jul 7, 2026 | ||
| Backdoor Defense | GTSRB | 118 | Jun 23, 2026 | ||
| Code | HumanEval | 118 | Jun 2, 2026 | ||
| Social Commonsense Reasoning | SIQA | 118 | Jul 8, 2026 | ||
| Denoising | BSD68 sigma=25 | 118 | May 13, 2026 | ||
| Language Modeling | OpenWebText (val) | 118 | Jul 3, 2026 | ||
| Mathematical Reasoning | GSM8K v1 (test) | 118 | Jun 2, 2026 | ||
| Code Generation | EvalPlus | 118 | Jun 12, 2026 | ||
| Physical Commonsense Reasoning | PIQA (val) | 118 | May 19, 2026 | ||
| Text Classification | AGNEWS | 118 | Feb 26, 2026 | ||
| Human-Object Interaction Detection | HICO-DET Known Object (test) | 118 | May 7, 2026 | ||
| Video Super-Resolution | REDS4 | 118 | Apr 23, 2026 | ||
| Domain Generalization | DomainBed (test) | 118 | May 29, 2026 | ||
| Image Classification | ImageNet 1% labeled | 118 | Feb 27, 2026 | ||
| Video Instance Segmentation | YouTube-VIS (val) | 118 | Feb 26, 2026 | ||
| Object Localization | PASCAL VOC 2007 (trainval) | 118 | Feb 26, 2026 |