Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2242 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Depth Completion | iBims | 16 | Feb 26, 2026 | ||
| Depth Completion | 7-Scenes | 16 | Feb 26, 2026 | ||
| Depth Completion | Metropolis 32-line | 16 | Feb 26, 2026 | ||
| Depth Completion | Metropolis 16-line | 16 | Feb 26, 2026 | ||
| Depth Completion | Metropolis 8-line | 16 | Feb 26, 2026 | ||
| Depth Completion | iBims < 5m | 16 | Feb 26, 2026 | ||
| Depth Completion | iBims 100 pts | 16 | Feb 26, 2026 | ||
| Depth Completion | iBims SIFT | 16 | Feb 26, 2026 | ||
| Depth Completion | 7-Scenes < 3m | 16 | Feb 26, 2026 | ||
| Depth Completion | 7-Scenes 100 pts | 16 | Feb 26, 2026 | ||
| Depth Completion | 7-Scenes SfM | 16 | Feb 26, 2026 | ||
| Depth Completion | ScanNet < 3m | 16 | Feb 26, 2026 | ||
| Depth Completion | ScanNet 100 pts | 16 | Feb 26, 2026 | ||
| Depth Completion | ScanNet SIFT (test) | 16 | Feb 26, 2026 | ||
| Classification | aPY | 16 | Feb 26, 2026 | ||
| Virtual Try-On | StreetTryOn Shop-to-Street | 16 | Mar 31, 2026 | ||
| Financial Open-ended QA | FinQA (test) | 16 | Feb 26, 2026 | ||
| Medical Multi-choice QA | MMedBench (test) | 16 | Feb 26, 2026 | ||
| Financial Open-ended Question Answering | FinQA (test) | 16 | Feb 26, 2026 | ||
| Medical Multi-choice Question Answering | MMedBench (test) | 16 | Feb 26, 2026 | ||
| Mathematical Reasoning | Macro Average AIME2024, MATH, Minerva, Olympiad-Bench | 16 | Feb 26, 2026 | ||
| Deep Research | BrowseComp-zh | 16 | Feb 26, 2026 | ||
| Regression | Airfoil UCIrvine (5-fold cross-validation) | 16 | Feb 26, 2026 | ||
| Regression | OpenML 618 (5-fold cross-validation) | 16 | Feb 26, 2026 | ||
| Regression | OpenML 586 (5-fold cross-validation) | 16 | Feb 26, 2026 |