Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 914 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Human Activity Recognition | MotionSense | 29 | May 20, 2026 | ||
| Vision-Language Navigation | R2R 1 (test unseen) | 29 | May 27, 2026 | ||
| Multimodal Understanding | LLaVAW | 29 | Jun 30, 2026 | ||
| Multi-view people detection | MultiviewX | 29 | Mar 26, 2026 | ||
| Code Generation | MBPP-S (test) | 29 | Feb 26, 2026 | ||
| Forecasting | Wind | 29 | Apr 21, 2026 | ||
| Multivariate long-term forecasting | ETTm1 (Avg) | 29 | Jun 1, 2026 | ||
| Motion Deblurring | GoPro synthetic (test) | 29 | May 5, 2026 | ||
| Abdominal Multi-organ Segmentation | Synapse | 29 | Mar 16, 2026 | ||
| Knowledge Graph Completion | UMLS | 29 | Jun 5, 2026 | ||
| Depth Estimation | KITTI improved dense ground truth | 29 | Feb 26, 2026 | ||
| Question Answering | ECQA, QASC, OBQA, ARC | 29 | Feb 26, 2026 | ||
| Pose estimation | KITTI-360 | 29 | Apr 1, 2026 | ||
| Machine Translation | WMT De-En 22 (test) | 29 | Feb 26, 2026 | ||
| Multimodal Entity Linking | WikiDiverse (test) | 29 | Jun 11, 2026 | ||
| Image Retrieval from Contextual Descriptions | IMAGECODE All (test) | 29 | Feb 26, 2026 | ||
| Reinforcement Learning | CartPole | 29 | May 12, 2026 | ||
| Temporal Link Prediction | ICEWS Interpolation 05-15 (test) | 29 | Mar 10, 2026 | ||
| Semantic Segmentation | Cityscapes (CS) 1024x512 (val) | 29 | Feb 26, 2026 | ||
| Multimodal Hate Speech Detection | Hateful Memes | 29 | Feb 26, 2026 | ||
| Medical Image Classification | DET10 | 29 | Feb 26, 2026 | ||
| Passage Ranking | NQ | 29 | Feb 26, 2026 | ||
| Code Generation | MBPP standard (test) | 29 | Mar 26, 2026 | ||
| Natural Language Reasoning | GSM8K, MATH, SVAMP, ASDiv, MAWPS, CARP | 29 | Feb 26, 2026 | ||
| Mathematical Reasoning | CARP | 29 | Feb 26, 2026 |