Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1049 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Code Generation | Average dataset-weighted (test) | 26 | May 25, 2026 | ||
| Code Generation | CodeForces (test) | 26 | May 25, 2026 | ||
| Code Generation | LiveBench (test) | 26 | May 25, 2026 | ||
| Language Modeling | FineWeb 10BT (train) | 26 | May 25, 2026 | ||
| Node Classification | Cora (test) | 26 | May 25, 2026 | ||
| Science Question Answering | ScienceQA | 26 | May 25, 2026 | ||
| Mathematical Reasoning | MATH | 26 | Jun 30, 2026 | ||
| Time-series Classification | PTB 2 classes | 26 | May 22, 2026 | ||
| Time-series Classification | APAVA 2 classes | 26 | May 22, 2026 | ||
| 2-class EEG classification | APAVA EEG-2 (Cross-subject) | 26 | May 22, 2026 | ||
| Zero-shot Downstream Evaluation | Downstream Suite Zero-shot (ARC-E, ARC-C, HellaS., PIQA, WG, OBQA, SciQ, BoolQ) | 26 | May 21, 2026 | ||
| Code Generation | HumanEval | 26 | May 20, 2026 | ||
| Ternary claim verification | AVeriTeC (test) | 26 | May 20, 2026 | ||
| Ternary claim verification | TFU (test) | 26 | May 20, 2026 | ||
| Question Answering | SQuAD v2 | 26 | May 20, 2026 | ||
| Language Modeling | SlimPajama latest (val) | 26 | May 20, 2026 | ||
| Classification | Census KDD | 26 | May 20, 2026 | ||
| Mathematical Reasoning | AIME 2024 | 26 | Jul 7, 2026 | ||
| Visual Question Answering | Visual Question Answering Evaluation Suite TVQA, InfoVQA, ChartQA, DocVQA, VizWiz | 26 | May 20, 2026 | ||
| Job Shop Scheduling | JSP instances 100 (test) | 26 | May 20, 2026 | ||
| Node Classification | Ele-Photo | 26 | Jun 4, 2026 | ||
| Commonsense Reasoning | Commonsense Tasks | 26 | May 19, 2026 | ||
| Affordance Prediction | AGD20K unseen | 26 | Jun 30, 2026 | ||
| Language Modeling | Language Modeling | 26 | May 19, 2026 | ||
| Multimodal Understanding | MMStar | 26 | May 21, 2026 |