Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1379 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Short-term forecasting | EPF NP | 22 | Mar 26, 2026 | ||
| Symbolic Regression | LSR-Synth | 22 | Feb 27, 2026 | ||
| Image Classification | CIFAR-100 (test) | 22 | Feb 27, 2026 | ||
| Image Classification | CIFAR-100 WRN34-10 (test) | 22 | Feb 27, 2026 | ||
| Multi-Hop Question Answering | HotpotQA (in-domain) | 22 | May 29, 2026 | ||
| AI-generated image detection | SDXL | 22 | May 21, 2026 | ||
| Micro-expression Recognition | SAMM | 22 | Mar 18, 2026 | ||
| Visual Question Answering | VQA v2 | 22 | Feb 27, 2026 | ||
| Dance-to-Music | AIST++ | 22 | Mar 4, 2026 | ||
| Puzzle Solving | 8-Puzzle | 22 | Feb 27, 2026 | ||
| Task recognition | COIN | 22 | Mar 4, 2026 | ||
| Spatial Reasoning | CV-Bench | 22 | May 20, 2026 | ||
| Code generation | HumanEval | 22 | Feb 26, 2026 | ||
| Emotion Distribution Learning | DMER subject-independent (test) | 22 | Feb 26, 2026 | ||
| Image Captioning | COCO 2017 (test) | 22 | Feb 26, 2026 | ||
| OOD Detection | CIFAR-100 OOD (test) | 22 | Mar 30, 2026 | ||
| Conformal Prediction | 89_pegase (test) | 22 | Feb 26, 2026 | ||
| 3D Scene Reconstruction | MipNeRF360 Indoor (test) | 22 | May 13, 2026 | ||
| Perturbation prediction | Replogle | 22 | Mar 19, 2026 | ||
| Perturbation prediction | Tahoe100M | 22 | Mar 19, 2026 | ||
| Perturbation prediction | PBMC | 22 | Mar 19, 2026 | ||
| Bayesian network structure discovery | disputed3 | 22 | Feb 26, 2026 | ||
| Bayesian network structure discovery | covid | 22 | Feb 26, 2026 | ||
| Bayesian network structure discovery | blockchain | 22 | Feb 26, 2026 | ||
| Causal Effect Identifiability | Synthetic Causal Graphs | 22 | Feb 26, 2026 |