Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 725 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Pedagogical Dialogue Evaluation | SHAPE (test) | 33 | Apr 27, 2026 | ||
| Open-domain QA | Bambogle v1 (out-of-domain) | 33 | Apr 27, 2026 | ||
| Binary Classification | Bank Marketing public (CV) | 33 | Apr 24, 2026 | ||
| Classification | Wine Quality (3 CV seeds) | 33 | Apr 24, 2026 | ||
| Multiclass classification | Glass Identification (test) | 33 | Apr 24, 2026 | ||
| Mathematical Reasoning | GSM8K | 33 | Apr 24, 2026 | ||
| Mathematical Reasoning | MATH500 | 33 | Apr 24, 2026 | ||
| Text-based Visual Question Answering | TextVQA | 33 | May 26, 2026 | ||
| Node Classification | ArXiv 2023 | 33 | Apr 28, 2026 | ||
| Text-to-SQL | BIRD | 33 | Jul 3, 2026 | ||
| Math | AMC23 | 33 | Jun 2, 2026 | ||
| Machine Unlearning | TOFU | 33 | Jun 4, 2026 | ||
| Visual Question Answering | XLRS-Bench L-3 Capability (test) | 33 | May 11, 2026 | ||
| Image Classification | ImageNet 1k | 33 | Apr 28, 2026 | ||
| Text-to-Image Generation | GenEval (val) | 33 | Apr 15, 2026 | ||
| Lifelong Model Editing | CounterFact | 33 | Apr 14, 2026 | ||
| Hallucination Detection | SciQ | 33 | Apr 14, 2026 | ||
| Spatiotemporal chaos forecasting | Kuramoto-Sivashinsky (KS) system | 33 | Jul 2, 2026 | ||
| Multi-task Knowledge | MMLU-Pro | 33 | Apr 29, 2026 | ||
| Document Reranking | TREC DL 20 | 33 | Apr 30, 2026 | ||
| Dataset Inference | ImageNet 1k | 33 | Apr 10, 2026 | ||
| Sarcasm Detection | MSD | 33 | Apr 10, 2026 | ||
| Anomaly Detection | Traffic Scene Anomaly Detection (balanced split of 1000 examples) | 33 | Apr 9, 2026 | ||
| Bivariate Causal Discovery | NN-V | 33 | Apr 7, 2026 | ||
| Bivariate Causal Discovery | Qd-V | 33 | Apr 7, 2026 |