Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 617 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-modal sarcasm detection | MMSD 2.0 | 37 | May 21, 2026 | ||
| Motion Prediction | Argoverse official leaderboard (test) | 37 | Mar 31, 2026 | ||
| Musical Instrument Classification | OpenMIC (test) | 37 | Feb 26, 2026 | ||
| Sentiment Analysis | IMDB (test) | 37 | Feb 26, 2026 | ||
| Factual Consistency Evaluation | TRUE benchmark | 37 | Feb 26, 2026 | ||
| Linear Classification | ImageNet 1k (val) | 37 | Feb 26, 2026 | ||
| Few-Shot Object Detection | MS COCO Novel Classes | 37 | Feb 26, 2026 | ||
| Low-light Image Enhancement | LOL v2 | 37 | Mar 16, 2026 | ||
| Oriented Object Detection | DOTA 1.5 (val) | 37 | Mar 4, 2026 | ||
| OOD Detection | ImageNet Average | 37 | Feb 26, 2026 | ||
| Abnormal Event Detection | Avenue (test) | 37 | Feb 26, 2026 | ||
| Temporal Action Detection | THUMOS14 (test) | 37 | Apr 23, 2026 | ||
| Semantic Segmentation | SemanticKITTI | 37 | Jun 19, 2026 | ||
| Image Classification | ImageNet-1K (val) | 37 | Feb 26, 2026 | ||
| Vision-and-Language Navigation | SOON (val unseen) | 37 | Jun 4, 2026 | ||
| Remote Grounding | REVERIE (val seen) | 37 | May 27, 2026 | ||
| Few-Shot Class-Incremental Learning | CUB200 (incremental sessions) | 37 | Feb 26, 2026 | ||
| Texture Classification | KTH 2-b | 37 | May 28, 2026 | ||
| Speech Recognition | Switchboard | 37 | Jun 18, 2026 | ||
| Traveling Salesman Problem (TSP) | TSP n=150 Generalization 1K instances | 37 | Jun 30, 2026 | ||
| Trojan Detection | GTSRB | 37 | May 21, 2026 | ||
| Super-resolution | NAMIC T2w (test) | 37 | Feb 26, 2026 | ||
| Whole tumor segmentation | BraTS 2018 (test) | 37 | Jun 9, 2026 | ||
| Lip Reading | LRW 1.0 (test) | 37 | Feb 26, 2026 | ||
| Single Object Detection | Pascal VOC 2012 | 37 | Mar 20, 2026 |