Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1157 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| User-level depression detection | SWDD (test) | 24 | Jul 7, 2026 | ||
| Novel View Synthesis | DL3DV 16 Views | 24 | Jul 7, 2026 | ||
| Novel View Synthesis | DL3DV 9 Views | 24 | Jul 7, 2026 | ||
| Multimodal Understanding | MME | 24 | Jul 7, 2026 | ||
| Visual Question Answering | POPE GQA | 24 | Jul 7, 2026 | ||
| Visual Question Answering | POPE A-OKVQA | 24 | Jul 7, 2026 | ||
| Visual Question Answering | POPE MSCOCO | 24 | Jul 7, 2026 | ||
| Prescription Prediction | TCM-BEST4SDT (test) | 24 | Jul 7, 2026 | ||
| Relevance Score Detection | BanglaMemeEvidence | 24 | Jul 7, 2026 | ||
| Malicious Package Detection | PyPI Malicious Package Dataset All Packages Combined (test) | 24 | Jul 7, 2026 | ||
| Cholangiocellular carcinoma (CCA) detection | Cholangiocellular carcinoma (CCA) | 24 | Jul 7, 2026 | ||
| Uncertainty & Selective Classification | CIFAR-100 1.0 (test) | 24 | Jul 7, 2026 | ||
| Robustness | CIFAR-100 1.0 (test) | 24 | Jul 7, 2026 | ||
| Image Restoration | CCDD-11 (test) | 24 | Jul 7, 2026 | ||
| Information Seeking | InfoSeek | 24 | Jul 7, 2026 | ||
| High-Resolution Multi-modal Search | HR-MMSearch | 24 | Jul 7, 2026 | ||
| Multi-modal Search | MMSearch | 24 | Jul 7, 2026 | ||
| Video Search Question Answering | VSQA | 24 | Jul 7, 2026 | ||
| Video Deep Research | VideoDR | 24 | Jul 7, 2026 | ||
| Fake Video Detection | ViF-Bench | 24 | Jul 7, 2026 | ||
| Tool Use | Multi-Calculator | 24 | Jul 7, 2026 | ||
| Tool Use | Single-Calculator | 24 | Jul 7, 2026 | ||
| Nested-calculator calculation | MedCalc-Pro 1.0 (test) | 24 | Jul 7, 2026 | ||
| future edge prediction | Enron DyGLib (transductive) | 24 | Jul 7, 2026 | ||
| future edge prediction | MOOC DyGLib (transductive) | 24 | Jul 7, 2026 |