Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 375 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Regression | UCI CONCRETE (test) | 51 | Jun 2, 2026 | ||
| Time Series Reconstruction | MuJoCo (test) | 51 | Feb 26, 2026 | ||
| 2d Darcy Flow | 2d Darcy Flow (test) | 51 | Feb 26, 2026 | ||
| Fine-grained classification | FGVC Aircraft | 51 | Jun 23, 2026 | ||
| Classification | MLLMU-Bench Forget Set | 51 | Jun 2, 2026 | ||
| Video Question-Answering | VideoMME wo sub | 51 | Feb 26, 2026 | ||
| Harmful meme detection | MAMI (test) | 51 | Jun 1, 2026 | ||
| Visual Question Answering | HRBench 8K | 51 | Apr 15, 2026 | ||
| Story Reasoning | XStoryCloze | 51 | May 14, 2026 | ||
| Future edge prediction | UCI (inductive) | 50 | Jul 7, 2026 | ||
| transductive future edge prediction | UCI | 50 | Jul 7, 2026 | ||
| Object Detection | Cityscapes → Foggy Cityscapes DINO (target-label budget 5%) | 50 | Jul 1, 2026 | ||
| System Prompt Exfiltration | Cline Agent Environment | 50 | Jun 30, 2026 | ||
| Time Series Forecasting | Traffic | 50 | Jun 19, 2026 | ||
| Time Series Forecasting | ETTh2 | 50 | Jun 19, 2026 | ||
| Diameter Estimation | Metal dataset (test) | 50 | Jun 12, 2026 | ||
| Text-to-Image Generation | GenEval2 In-Domain | 50 | Jun 11, 2026 | ||
| Load forecasting | Second Competition Dataset (test) | 50 | Jun 9, 2026 | ||
| Load Forecasting | UT Austin dataset (test) | 50 | Jun 9, 2026 | ||
| Load Forecasting | First Competition Dataset | 50 | Jun 9, 2026 | ||
| Clustering | JAFFE (test) | 50 | Jun 5, 2026 | ||
| Clustering | Yale Database | 50 | Jun 5, 2026 | ||
| Legal Work Product Review | Harvey LAB | 50 | Jun 4, 2026 | ||
| Question Answering | MMLU | 50 | Jun 2, 2026 | ||
| Question Answering | MedQA | 50 | Jun 2, 2026 |