Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 646 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Auditing Data Removal | MNIST Memorized (train folds M1-M5) | 36 | Feb 26, 2026 | ||
| Image Classification | ImageNet-C | 36 | Apr 20, 2026 | ||
| Question Answering | MOCHA (test) | 36 | Feb 26, 2026 | ||
| Summarization | Newsroom (test) | 36 | Feb 26, 2026 | ||
| Recommendation | Baby | 36 | Apr 27, 2026 | ||
| Mathematical Reasoning | Minerva MATH500 | 36 | May 22, 2026 | ||
| Backdoor Certification | ImageNette (test) | 36 | Feb 26, 2026 | ||
| Controllable Generation | Code-UltraFeedback | 36 | Feb 26, 2026 | ||
| Controllable Generation | HelpSteer2 | 36 | Feb 26, 2026 | ||
| Long-context Reasoning | Long-context Benchmarks 100K context LB-V2 DocMath Frames LB-MQA (test) | 36 | Feb 26, 2026 | ||
| Long-context Reasoning | Long-context Benchmarks 16K context DocMath Frames LB-MQA V2 (test) | 36 | Feb 26, 2026 | ||
| MAP Inference | Synthetic Pairwise MRF Random | 36 | Feb 26, 2026 | ||
| MAP Inference | Synthetic Pairwise MRF Potts | 36 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | CIFAR-10 | 36 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 | 36 | Feb 26, 2026 | ||
| Image Classification | CIFAR10 (test) | 36 | Feb 26, 2026 | ||
| Concept leakage evaluation | aPY | 36 | Feb 26, 2026 | ||
| Concept leakage evaluation | AwA2 | 36 | Feb 26, 2026 | ||
| Goal Recognition | MiniGrid Suboptimal trajectories | 36 | Feb 26, 2026 | ||
| Goal Recognition | MiniGrid (test) | 36 | Feb 26, 2026 | ||
| Multivariate long-term time series forecasting | Electricity | 36 | Feb 26, 2026 | ||
| Instruction Following | IFBench (test) | 36 | Jun 30, 2026 | ||
| Question Answering | PiQA | 36 | Mar 4, 2026 | ||
| Utterance Analysis | Toronto NeuroFace Only Audio (test) | 36 | Feb 26, 2026 | ||
| Utterance Analysis | Toronto NeuroFace Only Video (test) | 36 | Feb 26, 2026 |