Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 147 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Monocular Depth Estimation | KITTI | 92 | Jul 7, 2026 | ||
| Reasoning | GPQA | 92 | Jun 11, 2026 | ||
| Reasoning | GPQA | 92 | Jun 11, 2026 | ||
| Composed Image Retrieval | FashionIQ Shirt | 92 | Jul 3, 2026 | ||
| Audio-to-Text Retrieval | Clotho (test) | 92 | Jul 1, 2026 | ||
| Few-shot 3D Classification | ModelNet40 (test) | 92 | Feb 26, 2026 | ||
| Instruction Following | IFEval (test) | 92 | Jun 23, 2026 | ||
| Novel View Synthesis | Mip-NeRF 360 12-view | 92 | Jul 7, 2026 | ||
| Conditional Image Generation | ImageNet 512x512 (val) | 92 | Apr 1, 2026 | ||
| Multi-Task Incremental Learning | MTIL Order II | 92 | Jun 16, 2026 | ||
| Text-to-Video Generation | T2V-CompBench | 92 | May 15, 2026 | ||
| Multitask Knowledge | MMLU | 92 | Jun 2, 2026 | ||
| Image Classification | ImageNet-1K 1.0 (val) | 92 | Feb 26, 2026 | ||
| Document Question Answering | DocVQA (test) | 92 | Apr 21, 2026 | ||
| OOD Detection | ImageNet-1k ID Average OOD | 92 | May 26, 2026 | ||
| Image Classification | ImageNet-S | 92 | May 12, 2026 | ||
| Visual Question Answering | A-OKVQA (val) | 92 | Apr 21, 2026 | ||
| Visual Object Tracking | TNL2k (test) | 92 | May 12, 2026 | ||
| Video Compression | MCL-JCV | 92 | Jun 29, 2026 | ||
| Classification | CelebA (test) | 92 | Feb 27, 2026 | ||
| Image Classification | VisDA 2017 (test) | 92 | Apr 30, 2026 | ||
| 3D Point Cloud Classification | ScanObjectNN (test) | 92 | Mar 12, 2026 | ||
| Action Recognition | Diving-48 (test) | 92 | Apr 23, 2026 | ||
| Commonsense Question Answering | CommonSenseQA | 92 | May 29, 2026 | ||
| Image Classification | ImageNet 1k (10% labels) | 92 | Feb 26, 2026 |