Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2019 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Instrument Segmentation | EndoVis 2017 (t=1) & 2018 (t=2) (test) | 17 | Apr 6, 2026 | ||
| Instrument Segmentation | CholecSeg8k M2CAI-Seg (last episode) | 17 | Apr 6, 2026 | ||
| 3D Visual Question Answering | ScanQA | 17 | May 7, 2026 | ||
| Medical Visual Question Answering | SLAKE Closed | 17 | Apr 6, 2026 | ||
| Revenue Uplift Modeling | Synthetic Dataset | 17 | Apr 6, 2026 | ||
| Action Understanding | MMT-47 Action Understanding | 17 | Apr 6, 2026 | ||
| Object Motion and Spatial Reasoning | MMT-47 Object Motion & Spatial | 17 | Apr 6, 2026 | ||
| High Level Reasoning | MMT-47 High Level Reasoning | 17 | Apr 6, 2026 | ||
| Natural Language Understanding | GLUE | 17 | Apr 6, 2026 | ||
| Commonsense Reasoning | MMT-47 Commonsense Reasoning | 17 | Apr 6, 2026 | ||
| Image Classification | MMT-47 | 17 | Apr 6, 2026 | ||
| Vision Understanding | MMT-47 Vision Benchmark | 17 | Apr 6, 2026 | ||
| OS agent GUI interaction | VeriOS-Bench | 17 | Apr 6, 2026 | ||
| Textual Emotion Analysis | DFEC internally curated 2025 (test) | 17 | Apr 6, 2026 | ||
| Visual Spatial Planning | VSP (test) | 17 | Jun 4, 2026 | ||
| Node classification | Squirrel Poisoned | 17 | Apr 3, 2026 | ||
| Node classification | Chameleon Poisoned | 17 | Apr 3, 2026 | ||
| Node classification | Actor Poisoned | 17 | Apr 3, 2026 | ||
| Node classification | Pubmed Poisoned | 17 | May 8, 2026 | ||
| Node classification | Citeseer Poisoned | 17 | May 8, 2026 | ||
| Node classification | Cora Poisoned | 17 | Apr 3, 2026 | ||
| Referring Expression Comprehension | KVG-Bench | 17 | Apr 3, 2026 | ||
| rPPG estimation | UBFC-rPPG | 17 | Apr 3, 2026 | ||
| Label shift estimation | MNIST Dirichlet shift alpha=10 (val size=2000) | 17 | Apr 3, 2026 | ||
| Label shift estimation | MNIST Dirichlet shift alpha=10 size=1500 (val) | 17 | Apr 3, 2026 |