Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1855 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Interactive Segmentation | PAPILA | 18 | Apr 10, 2026 | ||
| Interactive Segmentation | G1020 | 18 | Apr 10, 2026 | ||
| Interactive Image Segmentation | ATLAS T1 | 18 | Apr 10, 2026 | ||
| Interactive Image Segmentation | TBI T1 | 18 | Apr 10, 2026 | ||
| Interactive Image Segmentation | WMH Flair | 18 | Apr 10, 2026 | ||
| Interactive Image Segmentation | TBI Flair | 18 | Apr 10, 2026 | ||
| Video-based Person Re-identification | iLIDS-VID v1 (test) | 18 | Apr 10, 2026 | ||
| Long-context Understanding | Average Overall | 18 | Apr 10, 2026 | ||
| Prompt Injection | SQuAD Inj | 18 | Apr 10, 2026 | ||
| CO2 Estimation | XA→BJ (test) | 18 | Apr 10, 2026 | ||
| Population Estimation | XA→BJ (test) | 18 | Apr 10, 2026 | ||
| GDP Estimation | XA→BJ (test) | 18 | Apr 10, 2026 | ||
| Population Prediction | BJ to CD transfer (BJ(X)/CD(Y)) | 18 | Apr 10, 2026 | ||
| Computational Latency Measurement | Temperature Sensing Data | 18 | Apr 10, 2026 | ||
| Global sensemaking | 83 global sensemaking questions | 18 | Apr 10, 2026 | ||
| Knowledge-to-action question answering | 50 knowledge-to-action questions | 18 | Apr 10, 2026 | ||
| Science Reasoning | GPQA | 18 | Jun 9, 2026 | ||
| Semantic Segmentation | LandCover.ai (test) | 18 | May 1, 2026 | ||
| Fake News Video Detection | FakeTT | 18 | Apr 10, 2026 | ||
| Cross-domain image retrieval | Office-Home | 18 | Apr 9, 2026 | ||
| Hit discovery (DMTA replay) | DUD-E | 18 | Apr 9, 2026 | ||
| Multimodal Deep Search | MMSrch | 18 | Apr 9, 2026 | ||
| AR-SSVEP decoding | Six-class outdoor AR-SSVEP experiment (online) | 18 | Apr 9, 2026 | ||
| Cross-domain recommendation | Amazon Reviews Movies → Music | 18 | Apr 29, 2026 | ||
| Classification | Yale HER2 | 18 | Apr 9, 2026 |