Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 775 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-Agent Path Finding (MAPF) | den312d 65x81 | 32 | Feb 26, 2026 | ||
| Classification | 20News | 32 | Feb 26, 2026 | ||
| Classification | TImageNet | 32 | Feb 26, 2026 | ||
| Real estate price index forecasting | Dubai Weekly Real Estate Price Index Long Horizon | 32 | Feb 26, 2026 | ||
| Real estate price index forecasting | Dubai Weekly Real Estate Price Index Medium Horizon | 32 | Feb 26, 2026 | ||
| Real estate price index forecasting | Dubai Weekly Real Estate Price Index Short Horizon | 32 | Feb 26, 2026 | ||
| Face Recognition | IJB-C (test) | 32 | Feb 26, 2026 | ||
| Face Recognition | BRIAR Protocol 3.1 | 32 | Feb 26, 2026 | ||
| Next Token Prediction | QMSum | 32 | Feb 26, 2026 | ||
| Next Token Prediction | WildChat | 32 | Feb 26, 2026 | ||
| Next Token Prediction | BBC | 32 | Feb 26, 2026 | ||
| Science Question Answering | ARC-C | 32 | Mar 10, 2026 | ||
| OpenBook Question Answering | OBQA | 32 | May 14, 2026 | ||
| Veracity Prediction | LIAR RAW | 32 | Apr 21, 2026 | ||
| Time Series Classification | UCR First Part (test) | 32 | Jul 1, 2026 | ||
| Degradation-induced covariate shift detection | COCO synthetically corrupted variants | 32 | Feb 26, 2026 | ||
| Person Re-Identification | CUHK03 Protocol-1 | 32 | Mar 16, 2026 | ||
| Point Cloud Registration | ModelNet40 RPMNet manner (Unseen Shapes) | 32 | Feb 26, 2026 | ||
| Question Answering | MRQA 2019 (dev) | 32 | Mar 12, 2026 | ||
| Web security task completion | XBOW 104 tasks | 32 | Mar 4, 2026 | ||
| EEG classification | Mental Arithmetic | 32 | Feb 26, 2026 | ||
| EEG classification | SEED | 32 | Feb 26, 2026 | ||
| EEG classification | ISRUC | 32 | Feb 26, 2026 | ||
| Knowledge Graph Retrieval | STaRK-Amazon 1.0 (Human) | 32 | Feb 26, 2026 | ||
| Next event prediction | Amazon | 32 | May 19, 2026 |