Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 701 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Text Summarization | CNN/DM | 34 | May 20, 2026 | ||
| Face Presentation Attack Detection | SIW-M v2 | 34 | May 14, 2026 | ||
| Translation | Translation | 34 | Jun 23, 2026 | ||
| Classification | MoleculeNet | 34 | Jun 4, 2026 | ||
| Long-Context Retrieval | RULER 16K | 34 | Jul 7, 2026 | ||
| Visual Question Answering | E-VQA | 34 | Jul 9, 2026 | ||
| Logical Reasoning | LogiQA | 34 | May 14, 2026 | ||
| Image Classification | CIFAR-100 LTN (Asymmetric Noise) (test) | 34 | Apr 28, 2026 | ||
| Image Classification | CIFAR-100-LTN Symmetric Noise (test) | 34 | Apr 28, 2026 | ||
| Image Classification | CIFAR-10-LTN Symmetric Noise (test) | 34 | Apr 28, 2026 | ||
| Image Classification | Img-LTNr (test) | 34 | Apr 28, 2026 | ||
| Mathematical Reasoning | GSM8K (test) | 34 | Apr 28, 2026 | ||
| General Knowledge Retention | General Utility | 34 | Apr 24, 2026 | ||
| 36h-ahead water level bias prediction | Hurricane Idalia 2023 (2 days around landfall) | 34 | Apr 23, 2026 | ||
| 36h-ahead water level bias prediction | Hurricane Idalia 2023 (test) | 34 | Apr 23, 2026 | ||
| 24h-ahead water level bias prediction | Hurricane Idalia 2 days around landfall 2023 | 34 | Apr 23, 2026 | ||
| 24h-ahead water level bias prediction | Hurricane Idalia Full 2023 (test) | 34 | Apr 23, 2026 | ||
| Certifying Identifiability | Acyclic Mixed Graphs 1000 Randomly Sampled (m=10 nodes, p=0.2) | 34 | Apr 23, 2026 | ||
| Visual Question Answering | OKVQA | 34 | Jun 11, 2026 | ||
| Interactive Environment Task Completion | ScienceWorld (Unseen) | 34 | Jun 8, 2026 | ||
| Multiple Choice Question Answering | PubMedQA (test) | 34 | Jun 2, 2026 | ||
| Vision-Language Understanding | Vision-Language Benchmark Suite Aggregate | 34 | Apr 21, 2026 | ||
| Multimodal Understanding | MMMU | 34 | May 19, 2026 | ||
| 3D Point Cloud Classification | ModelNet40 Clean (test) | 34 | Jun 18, 2026 | ||
| General Language Model Evaluation | Utility Set MMLU, BBH, TruthfulQA, TriviaQA, AlpacaEval | 34 | Apr 16, 2026 |