Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 780 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Embodied Question Answering | OpenEQA v1.0 (test) | 32 | Feb 26, 2026 | ||
| Adversarial Attack | MDC (full) | 32 | Feb 26, 2026 | ||
| Video Highlight Detection | QVHighlights | 32 | Apr 21, 2026 | ||
| Facial Expression Manipulation | Intra-identity (Intra-ID) | 32 | Feb 26, 2026 | ||
| Pulse Rate Estimation | VIPL-HR Intra-dataset | 32 | Jun 5, 2026 | ||
| Emotion Recognition | SEED-V (LOSO) | 32 | Mar 19, 2026 | ||
| Anomaly Detection | APPD (test) | 32 | Feb 26, 2026 | ||
| Mathematical Reasoning | MathVision Mini | 32 | Apr 23, 2026 | ||
| Multimodal Understanding | AI2D | 32 | May 11, 2026 | ||
| Visual Question Answering | UCIT | 32 | Jun 16, 2026 | ||
| Visual Question Answering | MLLM-DCL | 32 | Jun 16, 2026 | ||
| Video Reasoning | MMVU mc | 32 | Jun 11, 2026 | ||
| Raindrop Removal | RainDrop | 32 | Apr 23, 2026 | ||
| Class-incremental learning | Cars-196 | 32 | May 28, 2026 | ||
| BEV Object Detection | TJ4DRadSet (test) | 32 | Mar 13, 2026 | ||
| Document Parsing | OmniDocBench Real5 warping | 32 | Apr 6, 2026 | ||
| Document Parsing | OmniDocBench Real5 skewing variation | 32 | Apr 6, 2026 | ||
| Document Parsing | Real5-OmniDocBench (screen-photography) | 32 | Apr 6, 2026 | ||
| Reasoning | ProsQA | 32 | Jun 9, 2026 | ||
| Object Hallucination | MSCOCO POPE (test) | 32 | Mar 9, 2026 | ||
| Video Question Answering | Video-MME | 32 | Jul 3, 2026 | ||
| Over-refusal evaluation | MMMU in-scope (test) | 32 | Feb 26, 2026 | ||
| Over-refusal evaluation | ScienceQA in-scope (test) | 32 | Feb 26, 2026 | ||
| Depth Completion | KITTI Depth Completion official 1,000-frame 1216x352 (val) | 32 | Feb 26, 2026 | ||
| Hyperspectral Image Classification | KSC (test) | 32 | May 28, 2026 |