Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1799 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mixed-categorical optimization | fII dc = dx = 5 | 18 | Jun 12, 2026 | ||
| Image Deblurring | CBSD10 | 18 | Jun 12, 2026 | ||
| Out-of-Distribution Detection | POWDER RF fingerprinting Scenario C (bes-day1 and bes-day2 sampling) | 18 | Jun 12, 2026 | ||
| Visual Question Answering | ToS-TextVQA | 18 | Jun 12, 2026 | ||
| Image Captioning | ToS-TextCaps | 18 | Jun 12, 2026 | ||
| Tool Retrieval | RRB | 18 | Jun 12, 2026 | ||
| Tool Retrieval | G3 | 18 | Jun 12, 2026 | ||
| Tool Retrieval | G2 | 18 | Jun 12, 2026 | ||
| Tool Retrieval | G1 | 18 | Jun 12, 2026 | ||
| Operator Learning | MFC g-parameter family (OOD) | 18 | Jun 11, 2026 | ||
| Multi-programmed Throughput | SPEC CPU 2017 | 18 | Jun 11, 2026 | ||
| Web Search | BrowseComp | 18 | Jun 11, 2026 | ||
| Visible-Infrared Person Re-identification | RegDB Visible to Infrared | 18 | Jun 11, 2026 | ||
| Sequential Visual Localization | ScanNet cross-temporal v2 | 18 | Jun 11, 2026 | ||
| Sequential Visual Localization | 3RScan v1 (test) | 18 | Jun 11, 2026 | ||
| Safety Evaluation | MalwareBench | 18 | Jun 11, 2026 | ||
| Safety Evaluation | RMCBench | 18 | Jun 11, 2026 | ||
| Label Correction | RESISC45 | 18 | Jun 11, 2026 | ||
| Label Correction | OrganAMNIST | 18 | Jun 11, 2026 | ||
| Label Correction | FashionMNIST | 18 | Jun 11, 2026 | ||
| Static Spatial Reasoning | STI-Bench Static | 18 | Jun 11, 2026 | ||
| HCC (2 classes) classification | DISCO | 18 | Jun 11, 2026 | ||
| leukemia (2 classes) classification | DISCO | 18 | Jun 11, 2026 | ||
| age category (5 classes) classification | cMD3 | 18 | Jun 11, 2026 | ||
| body subsites (18 classes) classification | HMP | 18 | Jun 11, 2026 |