Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1445 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Brain Decoding | SEED-IV | 21 | May 19, 2026 | ||
| Multimodal Reasoning | MMMU-Pro | 21 | May 12, 2026 | ||
| Multi-agent system task solving | workbench | 21 | May 12, 2026 | ||
| Multi-agent system task solving | plancraft | 21 | May 12, 2026 | ||
| Multi-agent system task solving | browsecomp | 21 | May 12, 2026 | ||
| Multi-agent system task solving | finance | 21 | May 12, 2026 | ||
| Short-answer Question Answering | Natural Questions (NQ) | 21 | May 12, 2026 | ||
| Short-answer Question Answering | TriviaQA | 21 | May 12, 2026 | ||
| Factual Question Answering | TruthfulQA | 21 | May 12, 2026 | ||
| Class-conditional image generation | ImageNet 256x256 2015 (test) | 21 | May 12, 2026 | ||
| Place Recognition | KITTI360-AG (road map) | 21 | May 12, 2026 | ||
| Place Recognition | KITTI360-AG satellite | 21 | May 12, 2026 | ||
| Place Recognition | nuScenes-AG | 21 | May 12, 2026 | ||
| Context Compression | BenchPress short-context (test) | 21 | May 12, 2026 | ||
| Length of Stay (LOS) | MIMIC-IV | 21 | Jun 5, 2026 | ||
| Medical Question Answering | MedQA USMLE | 21 | Jun 4, 2026 | ||
| Planning | FORGE-BENCH | 21 | May 12, 2026 | ||
| Question Answering | CommonsenseQA (CSQA) (test) | 21 | May 12, 2026 | ||
| Question Answering | ARC-Challenge (ARC-C) (test) | 21 | May 12, 2026 | ||
| Novel View Synthesis | (test) | 21 | May 12, 2026 | ||
| Novel View Synthesis | Unspecified Dataset (train) | 21 | May 12, 2026 | ||
| Population Dynamics Interpolation | EB scRNA 5-dim PCA representation (leave-one-out) | 21 | May 12, 2026 | ||
| Scientific Question Answering | GPQA D | 21 | May 12, 2026 | ||
| Code Generation | HumanEval | 21 | May 12, 2026 | ||
| Mathematical Reasoning | AIME 24 | 21 | May 12, 2026 |