Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 248 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question Answering | GPQA Diamond | 65 | Jun 5, 2026 | ||
| Jailbreak Attack | AdvBench | 65 | Jun 4, 2026 | ||
| Image Classification | DTD (test) | 65 | Jun 30, 2026 | ||
| Long-context Reasoning | BABILong 8k | 65 | Apr 8, 2026 | ||
| Text-to-image generation | WISE | 65 | Jun 4, 2026 | ||
| Instruction Following | IFEval | 65 | May 29, 2026 | ||
| Math Reasoning | MultiArith | 65 | Apr 14, 2026 | ||
| Medical Question Answering | HeadQA | 65 | Jun 16, 2026 | ||
| Medical Question Answering | PubMedQA | 65 | May 14, 2026 | ||
| Open-vocabulary semantic segmentation | Pascal Context 60 | 65 | Jun 16, 2026 | ||
| Reward Modeling | HelpSteer (test) | 65 | May 8, 2026 | ||
| Question Answering | TriviaQA | 65 | Jun 1, 2026 | ||
| Mathematical Reasoning | GSM8K 200 PROBLEMS | 65 | Mar 6, 2026 | ||
| Myoelectric Gesture Recognition | Ninapro DB4 | 65 | Mar 6, 2026 | ||
| Study Outcome Prediction | Rel Trial | 65 | Jun 4, 2026 | ||
| Task addition | 8 Vision | 65 | May 20, 2026 | ||
| Classification | Vehicle | 65 | May 13, 2026 | ||
| Reasoning | AIME 24 | 65 | May 8, 2026 | ||
| Object Goal Navigation | HM3D v1 (val) | 65 | Jun 2, 2026 | ||
| Object-Goal Navigation | HM3D-OVON Seen (val) | 65 | Jun 2, 2026 | ||
| Reinforcement Learning | MountainCarContinuous v0 | 65 | May 12, 2026 | ||
| Reasoning | HLE | 65 | Jul 7, 2026 | ||
| Code Generation | HumanEval | 65 | Mar 4, 2026 | ||
| PDE Solving | PDEBench Diff.Sorp (test) | 65 | Mar 20, 2026 | ||
| Classification | 33 datasets missing rate <= 10% (test) | 65 | Feb 26, 2026 |