Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1400 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Regression | Boston | 22 | Jul 9, 2026 | ||
| Multivariate long-term series forecasting | Solar-Energy (test) | 22 | Feb 26, 2026 | ||
| Treatment Effect Estimation | NEWS semi-synthetic | 22 | Feb 26, 2026 | ||
| Treatment Effect Estimation | ACIC semi-synthetic 2017 | 22 | Feb 26, 2026 | ||
| Treatment Effect Estimation | RORCO Real | 22 | Feb 26, 2026 | ||
| Treatment Effect Estimation | NEWS semi-synthetic (test) | 22 | Feb 26, 2026 | ||
| Treatment Effect Estimation | JOBS semi-synthetic (test) | 22 | Feb 26, 2026 | ||
| Treatment Effect Estimation | ACIC semi-synthetic 2016 (test) | 22 | Feb 26, 2026 | ||
| Treatment Effect Estimation | RORCO semi-synthetic | 22 | Feb 26, 2026 | ||
| Action Unit Detection | BP4D+ | 22 | Apr 3, 2026 | ||
| Speech Emotion Recognition | MSP-Podcast | 22 | Mar 25, 2026 | ||
| Speech Emotion Recognition | IEMOCAP | 22 | Mar 26, 2026 | ||
| Tool Retrieval | ToolLens (test) | 22 | Jun 17, 2026 | ||
| Whole-body mesh recovery | EHF (test) | 22 | Mar 31, 2026 | ||
| Segmentation | ACDC (val) | 22 | Feb 26, 2026 | ||
| Legal Reasoning | CaseHOLD (test) | 22 | Mar 10, 2026 | ||
| Truthfulness Evaluation | TruthfulQA medical (test) | 22 | Feb 26, 2026 | ||
| Reasoning Video Object Segmentation | ReVOS 1.0 (test) | 22 | Feb 26, 2026 | ||
| Optic Disc/Cup segmentation | 7 datasets Optic Disc/Cup (test) | 22 | Feb 26, 2026 | ||
| Prostate Segmentation | Multi-site Prostate MRI (leave-one-domain-out) | 22 | Feb 26, 2026 | ||
| Image Classification | fastMRI v1.0 (test) | 22 | Feb 26, 2026 | ||
| Anomaly Segmentation | KSDD2 | 22 | Mar 4, 2026 | ||
| Question Answering | NaturalQuestions processed | 22 | Feb 26, 2026 | ||
| Emotion Classification | Emotion (Out-of-domain) | 22 | Feb 26, 2026 | ||
| Sentence Interpolation Smoothness | ARGO randomly sampled 200 sentence pairs | 22 | Feb 26, 2026 |