Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1726 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multimodal Reasoning | MMVet v1 (val) | 19 | Mar 5, 2026 | ||
| Multimodal Understanding | MMBench-CN v1.1 (dev) | 19 | Mar 5, 2026 | ||
| Multimodal Understanding | MME v1.0 (val) | 19 | Mar 5, 2026 | ||
| GPP prediction | FLUXNET | 19 | Mar 11, 2026 | ||
| Node Classification | Cora Planetoid public split | 19 | Mar 18, 2026 | ||
| Clustering | NS | 19 | Mar 9, 2026 | ||
| Mathematical Reasoning | MATH 500 | 19 | Mar 4, 2026 | ||
| Audio Understanding | MMAU audio | 19 | Jun 4, 2026 | ||
| Ship Trajectory Prediction | CFDP | 19 | Mar 4, 2026 | ||
| Ship Trajectory Prediction | CSJP | 19 | Mar 4, 2026 | ||
| Speech Enhancement | URGENT Challenge 2025 (non-blind test) | 19 | Mar 4, 2026 | ||
| Instruction-based Image Editing | GroundEdit-Bench | 19 | Mar 4, 2026 | ||
| Mathematical Reasoning | MATH | 19 | Mar 4, 2026 | ||
| Aggregate Multimodal Evaluation | Evaluation Suite Average | 19 | Mar 4, 2026 | ||
| Visual Question Answering | GQA | 19 | Mar 4, 2026 | ||
| Regression | elevator | 19 | Mar 4, 2026 | ||
| Multimodal Understanding | MMMU-Pro vision | 19 | Apr 29, 2026 | ||
| Adversarial Attack | Oxford Pets 2012 (test) | 19 | Mar 4, 2026 | ||
| Geometry | MATH-Vision (mini) | 19 | Mar 4, 2026 | ||
| Blood glucose prediction | T1DEXI | 19 | Mar 4, 2026 | ||
| Image Editing | ImgEdit GPT-4.1 (test) | 19 | Mar 4, 2026 | ||
| Web Phishing Detection | knowphish-dataset (test 1) | 19 | Mar 4, 2026 | ||
| ML Engineering | MLE-Bench official (test) | 19 | Mar 4, 2026 | ||
| Incremental Object Detection | COCO 2017 (70-10) | 19 | Mar 4, 2026 | ||
| Incremental Object Detection | COCO 2017 (40-40) | 19 | Mar 4, 2026 |