Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 56 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | AIME 24/25 | 171 | May 29, 2026 | ||
| Knowledge | MMLU | 171 | Jul 2, 2026 | ||
| Text-based Person Search | CUHK-PEDES (test) | 171 | May 15, 2026 | ||
| Image Dehazing | SOTS | 171 | May 19, 2026 | ||
| Interactive Segmentation | SBD | 171 | Feb 26, 2026 | ||
| Whole Slide Image classification | CAMELYON16 (test) | 171 | Jun 30, 2026 | ||
| Image Classification | 20 Vision Classification Tasks | 170 | Jun 23, 2026 | ||
| Automatic Speech Recognition | LibriSpeech (test-clean) | 170 | Jul 1, 2026 | ||
| Question Answering | PubMedQA (test) | 170 | Apr 21, 2026 | ||
| Multivariate long-term series forecasting | Electricity (test) | 170 | Mar 31, 2026 | ||
| Class-conditional Image Generation | ImageNet 64x64 | 170 | May 11, 2026 | ||
| Deblurring | RealBlur-R (test) | 170 | May 5, 2026 | ||
| Image Retrieval | Flickr30K | 170 | Jun 18, 2026 | ||
| Mathematical Reasoning | GSM-Hard | 169 | Feb 26, 2026 | ||
| Visual Question Answering | MMBench (MMB) | 169 | Jul 7, 2026 | ||
| Video Question Answering | MSVD | 169 | Jun 24, 2026 | ||
| Video Classification | Something-Something V2 (test) | 169 | Feb 26, 2026 | ||
| Node Classification | Computers | 169 | Apr 1, 2026 | ||
| Visual Object Tracking | TNL2K | 169 | Jun 24, 2026 | ||
| Visual Place Recognition | Nordland | 169 | Jul 2, 2026 | ||
| LiDAR Semantic Segmentation | nuScenes (val) | 169 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 NAS-Bench-201 (val) | 169 | May 22, 2026 | ||
| Semantic Segmentation | NYUD v2 | 169 | Jun 16, 2026 | ||
| Abstractive Text Summarization | CNN/Daily Mail (test) | 169 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL halfcheetah-medium-expert | 169 | May 28, 2026 |