Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1117 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Em Dash Frequency Analysis | Suppression Corpus LLM generations & human essays (test) | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic d=3, K=8, N=1600 | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic (d=3, K=8, N=800) | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic (d=3, K=8, N=400) | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic d=3, K=4, N=800 | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic d=3, K=4, N=400 | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic (d=3, K=4, N=200) | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic (d=3, K=2, N=400) | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic (d=3, K=2, N=200) | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic d=3, K=2, N=100 | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic (d=2, K=8, N=1600) | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic d=2, K=8, N=800 | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic (d=2, K=8, N=400) | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic (d=2, K=4, N=800) | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic (d=2, K=4, N=400) | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic d=2, K=4, N=200 | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic d=2, K=2, N=400 | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic (d=2, K=2, N=200) | 25 | Mar 31, 2026 | ||
| K-means Clustering | Synthetic d=2, K=2, N=100 | 25 | Mar 31, 2026 | ||
| Gaze Estimation | MPIIFaceGaze DM | 25 | Mar 31, 2026 | ||
| Cinematography language understanding | ShotBench 1.0 (test) | 25 | Mar 31, 2026 | ||
| 2D-3D Registration | 7-Scenes | 25 | May 11, 2026 | ||
| Anomaly Detection | Stock | 25 | Apr 23, 2026 | ||
| Video Question Answering | LVB | 25 | May 13, 2026 | ||
| Classical Planning | IPC Benchmarks | 25 | Mar 30, 2026 |