Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1041 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Motion Description | HumanML3D (test) | 27 | Feb 27, 2026 | ||
| Arithmetic Computation | GSM8k | 27 | Feb 26, 2026 | ||
| Arithmetic Computation | MATH | 27 | Feb 26, 2026 | ||
| Robot Manipulation | LIBERO LONG (test) | 27 | May 12, 2026 | ||
| Multimodal Intent Recognition | MIntRec | 27 | May 4, 2026 | ||
| Abstract graph generation | Ego small | 27 | Mar 13, 2026 | ||
| Face Forgery Detection | FF++ (HQ) | 27 | Feb 26, 2026 | ||
| Object Detection | SAR-Aircraft v1.0 (test) | 27 | Feb 26, 2026 | ||
| Question Answering | Truthful-QA | 27 | Feb 26, 2026 | ||
| Image Classification | Places 365 | 27 | May 13, 2026 | ||
| Mathematical Reasoning | Olympiad (test) | 27 | Jun 9, 2026 | ||
| Safety Evaluation | Wildguard (test) | 27 | Jun 9, 2026 | ||
| Image Reconstruction | CelebA | 27 | Mar 4, 2026 | ||
| Question Answering | SQUAD | 27 | Feb 26, 2026 | ||
| Question Answering | RealtimeQA | 27 | Feb 26, 2026 | ||
| Question Answering | FaithEval | 27 | Feb 26, 2026 | ||
| Person Re-Identification | LTCC CC protocol (test) | 27 | Feb 26, 2026 | ||
| Critical View of Safety recognition | EndoScapes-CVS201 (test) | 27 | Feb 26, 2026 | ||
| Harmful Meme Detection | HarM | 27 | May 6, 2026 | ||
| Word Similarity | SimVerb-3500 (test) | 27 | Feb 26, 2026 | ||
| 3D Human Pose Estimation | Shelf (test) | 27 | Feb 26, 2026 | ||
| Named Entity Recognition | WeiboNER | 27 | Feb 26, 2026 | ||
| Sentiment Steering | OpenWebText Neutral to Negative (test) | 27 | Feb 26, 2026 | ||
| Sentiment Steering | OpenWebText Neutral to Positive (test) | 27 | Feb 26, 2026 | ||
| Syntactic Generalization | SG | 27 | May 18, 2026 |