Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1106 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-physics Simulation | Poseidon CE-RPUI (test) | 25 | May 19, 2026 | ||
| Multi-physics Simulation | Poseidon NS-BB (test) | 25 | May 19, 2026 | ||
| Blind Image Quality Assessment | CSIQ | 25 | Jun 30, 2026 | ||
| Binary classification | Lycos 2017 (test) | 25 | May 19, 2026 | ||
| Binary classification | CICIDS 2017 (test) | 25 | May 19, 2026 | ||
| Multi-Object Tracking | CrowdedSalmon body parts (val) | 25 | May 19, 2026 | ||
| Mathematical Reasoning | Minerva | 25 | Jun 23, 2026 | ||
| Object Detection Explanation Faithfulness | MS-COCO | 25 | May 19, 2026 | ||
| Multilingual Mathematical Reasoning | MGSM Thai (test) | 25 | May 19, 2026 | ||
| Supervised Fine-Tuning | MMMLU Danish (test) | 25 | May 19, 2026 | ||
| Question Answering | TeleQuAD Non-IID | 25 | May 19, 2026 | ||
| Question Answering | TeleQuAD (IID) | 25 | May 19, 2026 | ||
| Image Captioning | COCO | 25 | May 19, 2026 | ||
| Longest element length estimation | LRX Cayley graph | 25 | May 19, 2026 | ||
| Operator Learning | CFDBench | 25 | May 18, 2026 | ||
| Operator Learning | PDEArena NS-cond | 25 | May 18, 2026 | ||
| Operator Learning | PDEArena NS | 25 | May 18, 2026 | ||
| Operator Learning | PDEBench CNS (η=0.1, ζ=0.01) | 25 | May 18, 2026 | ||
| Operator Learning | PDEBench CNS (η=0.1, ζ=0.1) | 25 | May 18, 2026 | ||
| Operator Learning | PDEBench CNS (η=1, ζ=0.01) | 25 | May 18, 2026 | ||
| Operator Learning | PDEBench CNS (η=1, ζ=0.1) | 25 | May 18, 2026 | ||
| Operator Learning | FNO-ν 1e-3 | 25 | May 18, 2026 | ||
| Operator Learning | FNO-ν (1e-4) | 25 | May 18, 2026 | ||
| Operator Learning | FNO-ν 1e-5 | 25 | May 18, 2026 | ||
| Bidirectional Retrieval | SARVLM-1M (test) | 25 | May 18, 2026 |