Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 144 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Response Selection | Douban Conversation Corpus (test) | 94 | Feb 26, 2026 | ||
| Polyp Segmentation | ETIS (test) | 94 | Mar 31, 2026 | ||
| Action Recognition | MSR Action3D (test) | 94 | Jun 24, 2026 | ||
| Digit Classification | MNIST (test) | 94 | Feb 26, 2026 | ||
| Molecular property prediction | BBBP (test) | 94 | May 18, 2026 | ||
| Offline Reinforcement Learning | D4RL halfcheetah-random | 94 | May 11, 2026 | ||
| Graph Classification | ENZYMES (10-fold cross-validation) | 94 | Jun 11, 2026 | ||
| Traffic Flow Forecasting | PEMS03 (test) | 94 | May 26, 2026 | ||
| Reasoning | BBH (test) | 94 | May 19, 2026 | ||
| Scene Classification | AID TR=50% | 94 | Feb 26, 2026 | ||
| Sign Language Translation | How2Sign (test) | 94 | Jun 30, 2026 | ||
| Image Editing | GEdit-Bench English | 94 | Apr 23, 2026 | ||
| Question Answering | HotPotQA | 93 | Jun 12, 2026 | ||
| Correlation to Model Behavior Differences | MNLI | 93 | May 18, 2026 | ||
| Correlation to Accuracy Difference | OGBN-Arxiv | 93 | May 18, 2026 | ||
| Embedding transformation robustness | 14 GNN datasets (Average) | 93 | May 8, 2026 | ||
| Image Classification | CIFAR-100 (test) | 93 | Jun 25, 2026 | ||
| Human Activity Recognition | OctoNet | 93 | Apr 3, 2026 | ||
| Classification | MNIST (test) | 93 | Jul 7, 2026 | ||
| Adversarial Attack Transferability | ImageNet (test) | 93 | Mar 17, 2026 | ||
| Adversarial Attack Transferability | ImageNet | 93 | Mar 17, 2026 | ||
| Adversarial Attack Transferability | ImageNet 1k (val) | 93 | Mar 17, 2026 | ||
| Language Modeling | LM1B | 93 | May 11, 2026 | ||
| Few-Shot Segmentation | DeepGlobe | 93 | Jul 1, 2026 | ||
| Knowledge Unlearning | WMDP bio | 93 | Jun 17, 2026 |