Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 197 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Math Reasoning | OlympiadBench | 76 | May 20, 2026 | ||
| General Reasoning | BBEH | 76 | Jun 9, 2026 | ||
| Sequential Recommendation | Amazon Sports | 76 | Jun 17, 2026 | ||
| New Intent Discovery | BANKING | 76 | Jun 2, 2026 | ||
| Image Classification | Oxford Pets | 76 | Jul 8, 2026 | ||
| PredCLS | Action Genome (test) | 76 | Apr 23, 2026 | ||
| Response Harmfulness Detection | XSTEST-RESP | 76 | Jun 1, 2026 | ||
| Point Tracking | TAP-Vid DAVIS (First) | 76 | Apr 15, 2026 | ||
| Audio Deepfake Detection | In-the-wild | 76 | Jun 19, 2026 | ||
| Image Super-Resolution | B100 x4 (test) | 76 | Jun 19, 2026 | ||
| Multi-modal Evaluation | MME (total) | 76 | Mar 9, 2026 | ||
| Grade School Math Word Problems | GSM8K | 76 | Jun 5, 2026 | ||
| Video-based generative performance | Video-ChatGPT benchmark | 76 | Feb 26, 2026 | ||
| Classification | SIIM | 76 | Jun 4, 2026 | ||
| Image Classification | ImageNet (val) | 76 | Feb 26, 2026 | ||
| Text-based Person Retrieval | ICFG-PEDES | 76 | Apr 21, 2026 | ||
| Data Poisoning Defense | CIFAR-10 (test) | 76 | Apr 1, 2026 | ||
| Complex Named Entity Recognition | MultiCoNER (test) | 76 | Feb 26, 2026 | ||
| Image Generation | FFHQ 64x64 | 76 | Mar 24, 2026 | ||
| Geometry Problem Solving | Geometry3K (test) | 76 | Jun 29, 2026 | ||
| Backdoor Defense | Average of four datasets (test) | 76 | Apr 13, 2026 | ||
| Image Denoising | SET14 | 76 | May 14, 2026 | ||
| Image Captioning | Flickr30K (Karpathy split) | 76 | Feb 27, 2026 | ||
| Few-Shot Semantic Segmentation | PASCAL-5^i | 76 | Jul 1, 2026 | ||
| Question Answering | ARC Challenge (val) | 76 | Apr 14, 2026 |