Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 800 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | SYN NUMBERS to SVHN (test) | 32 | Feb 26, 2026 | ||
| De novo structural elucidation | MassSpecGym (test) | 32 | Feb 26, 2026 | ||
| Vessel segmentation | FIVES | 32 | Jun 5, 2026 | ||
| Binary Classification | MoleculeNet HIV DeepChem (test) | 32 | Feb 26, 2026 | ||
| Multi-class Image Classification | DigestPath 2019 (test) | 32 | Feb 26, 2026 | ||
| Cardiac Segmentation | Average (ACDC, M&Ms, RandBias, RandGhosting, RandMotion, RandSpike) (out-of-domain) | 32 | Feb 26, 2026 | ||
| Conformal Prediction | CIFAR 100 | 32 | May 19, 2026 | ||
| Incremental Task Learning (ITL) | permuted-MNIST (test) | 32 | Feb 26, 2026 | ||
| Incremental Task Learning (ITL) | split-MNIST (test) | 32 | Feb 26, 2026 | ||
| Sequential Image Classification | MNIST ordered pixel-by-pixel 1.0 (test) | 32 | Feb 26, 2026 | ||
| PDE solving | Korteweg-de Vries (KdV) 1-D (test) | 32 | Feb 26, 2026 | ||
| Initial Structure to Relaxed Structure (IS2RS) | Open Catalyst OC20 (test) | 32 | Feb 26, 2026 | ||
| Binary classification | Synthesized persistence diagrams 100 (test) | 32 | Feb 26, 2026 | ||
| Graph Classification | NCI109 (10-fold cross-validation) | 32 | May 5, 2026 | ||
| Class-conditional image generation | ImageNet 1K 512x512 (test) | 32 | Feb 26, 2026 | ||
| Traveling Salesman Problem (Edge Prediction) | TSP (test) | 32 | Feb 26, 2026 | ||
| Multimodal Sentiment Analysis | CH-SIMS | 32 | Mar 18, 2026 | ||
| Point Cloud Upsampling | ShapeNet (test) | 32 | Feb 27, 2026 | ||
| Molecular Generation | ZINC250k (test) | 32 | May 4, 2026 | ||
| Molecular Generation | QM9 (test) | 32 | Mar 13, 2026 | ||
| Multimodal Understanding | SEED Bench Img | 32 | Feb 26, 2026 | ||
| Classification | MLLMU-Bench (Retain Set) | 32 | Jun 2, 2026 | ||
| Classification | MLLMU-Bench (test) | 32 | Jun 2, 2026 | ||
| Cloze | MLLMU-Bench (Forget Set) | 32 | Jun 2, 2026 | ||
| Action Recognition | UCF-101 | 32 | Feb 26, 2026 |