Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1301 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multimodal Visual Pattern Recognition | MMVP | 23 | May 13, 2026 | ||
| Spatial Understanding | SAT | 23 | Apr 29, 2026 | ||
| Visual Question Answering | General VQA VQAv2, VizWiz, GQA, TextVQA, MME | 23 | Apr 10, 2026 | ||
| Question Answering | SDQA | 23 | Jul 9, 2026 | ||
| Object Hallucination Mitigation | MS COCO (500 random samples) | 23 | Apr 8, 2026 | ||
| Multi-hop Reasoning | HotpotQA | 23 | Jun 2, 2026 | ||
| Affective Image Content Analysis | AICA-Bench | 23 | Apr 8, 2026 | ||
| Multimodal Action Recognition | UCF101 | 23 | Jun 11, 2026 | ||
| Medical Image Segmentation | MSD Pancreas | 23 | Jun 18, 2026 | ||
| Multi-task Language Understanding | MMLU-Pro | 23 | Jun 30, 2026 | ||
| Visual Document Retrieval | ViDoRe v2 (test) | 23 | May 12, 2026 | ||
| Overall Table Generation | ARXIV2TABLE | 23 | Apr 8, 2026 | ||
| Pairwise Value Extraction | ARXIV2TABLE | 23 | Apr 8, 2026 | ||
| Unary Value Extraction | ARXIV2TABLE | 23 | Apr 8, 2026 | ||
| Schema Content Overlap | ARXIV2TABLE | 23 | Apr 8, 2026 | ||
| Paper Selection | ARXIV2TABLE | 23 | Apr 8, 2026 | ||
| Natural Language Inference | MNLI | 23 | May 19, 2026 | ||
| Mathematical Reasoning | Mathematical Reasoning Suite (AIME24, Math500, Olympiad, AMC, Minerva) | 23 | May 11, 2026 | ||
| Image Captioning | ICBench short captions (test) | 23 | Apr 7, 2026 | ||
| PDE Solving | Plasticity Structured Mesh (test) | 23 | May 12, 2026 | ||
| AI-generated image detection | EvalGEN | 23 | May 15, 2026 | ||
| Common-sense reasoning | Chem OOD Large Shift | 23 | Jul 3, 2026 | ||
| Common-sense reasoning | ARC-C OOD Small Shift | 23 | Jul 3, 2026 | ||
| Classification | AICCE 1.0 (test) | 23 | Apr 7, 2026 | ||
| Bivariate Causal Discovery | Rbf-V | 23 | Apr 7, 2026 |