Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 277 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Video depth estimation | TUM dynamics | 61 | May 15, 2026 | ||
| Multi-modal Retrieval | M-BEIR (test) | 61 | Jun 19, 2026 | ||
| Code Generation | HumanEval | 61 | Mar 6, 2026 | ||
| Multimodal Question Answering | ScienceQA | 61 | Jun 1, 2026 | ||
| Multiple Choice Video Question Answering | EgoSchema | 61 | Feb 26, 2026 | ||
| Knowledge Editing | MMEdit E-VQA | 61 | Feb 26, 2026 | ||
| Video Depth Estimation | Sintel (test) | 61 | Apr 10, 2026 | ||
| 3D Object Classification | ModelNet40 1k P | 61 | Feb 26, 2026 | ||
| text-to-motion synthesis | KIT-ML | 61 | Jul 9, 2026 | ||
| 4x Super-resolution | FFHQ 256x256 | 61 | Jun 30, 2026 | ||
| Multi-label classification | MS-COCO (val) | 61 | May 1, 2026 | ||
| Semantic Segmentation | WHU dataset (test) | 61 | Mar 4, 2026 | ||
| Few-shot 3D Scene Segmentation | ScanNet Avg | 61 | Feb 26, 2026 | ||
| 3D Classification | Objaverse LVIS | 61 | Jun 2, 2026 | ||
| Image Denoising | Kodak24 | 61 | Mar 17, 2026 | ||
| Hallucination and Visual Reasoning Evaluation | HallusionBench | 61 | Jun 30, 2026 | ||
| Classification | CIFAR-100 | 61 | Apr 20, 2026 | ||
| Image Classification | CIFAR-100 (test) | 61 | Feb 26, 2026 | ||
| 3D Semantic Segmentation | Replica | 61 | Jul 1, 2026 | ||
| Low-Light Image Enhancement | LOL synthetic v2 | 61 | Jul 7, 2026 | ||
| Jailbreak evaluation | Harmful Prompts Curated April 13, 2023 | 61 | Feb 26, 2026 | ||
| Top-level Implicit Discourse Relation Recognition | PDTB 2.0 (Ji split) | 61 | Feb 26, 2026 | ||
| Compositional Vision-Language Reasoning | Winoground | 61 | May 13, 2026 | ||
| Remote Sensing Change Detection | CLCD (test) | 61 | Feb 26, 2026 | ||
| Text-to-Video Generation | UCF-101 | 61 | Feb 26, 2026 |