Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2254 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | CUB-200 Task 1 100-20 classes | 16 | Feb 26, 2026 | ||
| Face Recognition | MS-Celeb-100 Task 4: 40-20 classes | 16 | Feb 26, 2026 | ||
| Face Recognition | MS-Celeb-100 Task 3: 60-20 classes | 16 | Feb 26, 2026 | ||
| Face Recognition | MS-Celeb-100 Task 2 80-20 classes | 16 | Feb 26, 2026 | ||
| Face Recognition | MS-Celeb-100 Task 1: 100-20 classes | 16 | Feb 26, 2026 | ||
| Image Classification | OmniBenchmark Task 4, 40-20 | 16 | Feb 26, 2026 | ||
| Image Classification | OmniBenchmark Task 3, 60-20 | 16 | Feb 26, 2026 | ||
| Image Classification | OmniBenchmark Task 2 80-20 | 16 | Feb 26, 2026 | ||
| Image Classification | OmniBenchmark Task 1, 100-20 | 16 | Feb 26, 2026 | ||
| Multi-Sentence Reading Comprehension | MultiRC | 16 | Feb 26, 2026 | ||
| CommitmentBank | CB | 16 | Feb 26, 2026 | ||
| White Matter Tractography | TractoInferno (test) | 16 | Feb 26, 2026 | ||
| Mathematical Reasoning | OlymMATH Easy | 16 | May 29, 2026 | ||
| Federated Graph Learning | Across-domain | 16 | Feb 26, 2026 | ||
| Federated Graph Learning | Social Across-dataset | 16 | Feb 26, 2026 | ||
| Federated Graph Learning | MUTAG | 16 | Feb 26, 2026 | ||
| Scheduling | AtCoder Heuristic Contest ahc058 (official leaderboard) | 16 | Apr 23, 2026 | ||
| Counterfactual Explanations | PneumoniaMNIST (test) | 16 | Feb 26, 2026 | ||
| Counterfactual Explanations | Spam (test) | 16 | May 28, 2026 | ||
| Counterfactual Explanations | Breast Cancer (test) | 16 | Feb 26, 2026 | ||
| Counterfactual Explanations | Credit (test) | 16 | Feb 26, 2026 | ||
| Clustering | YE | 16 | Feb 26, 2026 | ||
| General Language Evaluation | English lm-evaluation-harness | 16 | Apr 20, 2026 | ||
| Reinforcement Learning | Pusher | 16 | May 27, 2026 | ||
| Node Classification | CiteSeer Uniform Missing (test) | 16 | Feb 26, 2026 |