Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 552 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 3D scene reconstruction | ShapeNet Cars | 40 | Feb 26, 2026 | ||
| 3D Scene Representation | Multi-Object Scalability | 40 | Feb 26, 2026 | ||
| Classification | TissueMNIST | 40 | Jun 23, 2026 | ||
| Embedding Alignment | Natural Questions (test) | 40 | Feb 26, 2026 | ||
| Cancer sub-typing | DHMC-LUNG | 40 | Feb 26, 2026 | ||
| Cancer sub-typing | AMU-CSCC | 40 | Feb 26, 2026 | ||
| Cancer sub-typing | AMU-LSCC | 40 | Feb 26, 2026 | ||
| Question Answering | CoQA alpha = 0.25 (test) | 40 | Feb 26, 2026 | ||
| Question Answering | CoQA alpha = 0.25 (filtering stage) | 40 | Feb 26, 2026 | ||
| Entity classification | RelBench rel-stack user-badge | 40 | Jun 4, 2026 | ||
| Conversational Recommendation | REDIAL | 40 | Feb 26, 2026 | ||
| Mathematical Reasoning | GSM-Hard | 40 | May 26, 2026 | ||
| Robot Manipulation | Diverse Manipulation Tasks Put S in S | 40 | Feb 26, 2026 | ||
| Graduate-level Reasoning | GPQA Diamond | 40 | May 26, 2026 | ||
| Depth Estimation | ScanNet++ | 40 | Apr 8, 2026 | ||
| Instruction Following | AlpacaFarm (test) | 40 | Feb 26, 2026 | ||
| Change Point Detection | Variance change synthetic data | 40 | Feb 26, 2026 | ||
| Change-point detection | Synthetic high-dimensional data (variance change Σ = 2Id) | 40 | Feb 26, 2026 | ||
| Missing Imputation | MIMIC-III Laboratory Data subset (n=5000, p=24) under MAR | 40 | Feb 26, 2026 | ||
| Sparse Recovery | CelebA (test) | 40 | Feb 26, 2026 | ||
| Hyperspectral Image Super-Resolution | CAVE (test) | 40 | Jun 5, 2026 | ||
| Hyperspectral Image Super-Resolution | Pavia University | 40 | Mar 24, 2026 | ||
| Audio Identification | FMA (Free Music Archive) derived | 40 | Feb 26, 2026 | ||
| Robotic Manipulation | CALVIN D→D | 40 | Jun 30, 2026 | ||
| Robotic Manipulation | Push-T | 40 | Jun 4, 2026 |