Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1557 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| High-resolution perception | VStar | 20 | May 22, 2026 | ||
| Earth-science reasoning | MSEarthMCQ | 20 | May 22, 2026 | ||
| Microscopic reasoning | MicroVQA | 20 | May 22, 2026 | ||
| Chart parsing | ChartQA | 20 | May 22, 2026 | ||
| Math Reasoning | MathVision | 20 | Jul 3, 2026 | ||
| MRI Reconstruction | CC359 brain 2004 (test) | 20 | May 22, 2026 | ||
| MRI Reconstruction | fastMRI knee 2018 (test) | 20 | May 22, 2026 | ||
| Visual Grounding | MM-Conv Full NP 1.0 | 20 | May 22, 2026 | ||
| Video background subtraction | VIRAT 1.0 (verification) | 20 | May 22, 2026 | ||
| Multimodal Reasoning | VisualProcessBench Overall | 20 | May 22, 2026 | ||
| Multimodal Reasoning | MathVerse VO | 20 | May 22, 2026 | ||
| Multimodal Reasoning | MathVision | 20 | May 22, 2026 | ||
| Multimodal Reasoning | MMMU | 20 | May 22, 2026 | ||
| Hyperspectral Image Super-resolution | Kennedy Space Center | 20 | May 22, 2026 | ||
| Hyperspectral Image Super-Resolution | Pavia University Mean value of 80 LR HSI-HR MSI configurations | 20 | May 22, 2026 | ||
| Mathematical Reasoning | AIME 2025 | 20 | May 22, 2026 | ||
| General and STEM reasoning | SciBench | 20 | May 22, 2026 | ||
| General and STEM reasoning | MedQA | 20 | May 22, 2026 | ||
| General and STEM reasoning | HLE | 20 | May 22, 2026 | ||
| General and STEM reasoning | ChemBench | 20 | May 22, 2026 | ||
| General and STEM reasoning | CS-Bench | 20 | May 22, 2026 | ||
| Reasoning | HLE | 20 | May 21, 2026 | ||
| Spreadsheet Tasks | SSB (SpreadsheetBench) | 20 | May 21, 2026 | ||
| Root Estimation | Fitted Q-regression | 20 | May 21, 2026 | ||
| Anxiety Prediction | College Experience DS3 | 20 | May 21, 2026 |