Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1482 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Credit Risk Prediction | Home Credit Default Risk | 21 | Apr 21, 2026 | ||
| Image Classification | CIFAR-10 30% symmetric noise (test) | 21 | Feb 26, 2026 | ||
| Rebuttal Generation | Re2 (test) | 21 | Feb 26, 2026 | ||
| Reinforcement Learning | Atari 100K (test) | 21 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL Locomotion Full datasets | 21 | Mar 25, 2026 | ||
| Question Answering | MMLU | 21 | Apr 16, 2026 | ||
| Continuous Control | Humanoid 17-Dof | 21 | Feb 26, 2026 | ||
| Model Retrieval | Llama-8B model tree (test) | 21 | Feb 26, 2026 | ||
| Model Retrieval | Mistral-7B model tree (test) | 21 | Feb 26, 2026 | ||
| Model Retrieval | Qwen-7B model tree (test) | 21 | Feb 26, 2026 | ||
| Model Retrieval | Qwen-3B model tree (test) | 21 | Feb 26, 2026 | ||
| Code Generation | LiveCodeBench | 21 | Mar 24, 2026 | ||
| Classification Probing | Sarcasm (test) | 21 | Feb 26, 2026 | ||
| Classification Probing | HateXplain (test) | 21 | Feb 26, 2026 | ||
| Classification Probing | Counterfact (test) | 21 | Feb 26, 2026 | ||
| Classification Probing | Common (test) | 21 | Feb 26, 2026 | ||
| Classification Probing | Cities (test) | 21 | Feb 26, 2026 | ||
| Classification Probing | STSA (test) | 21 | Feb 26, 2026 | ||
| Multi-task Language Modeling | MergeBench | 21 | Apr 28, 2026 | ||
| Concept Erasure | Stable Diffusion Nudity Concept v1.4 | 21 | Jun 19, 2026 | ||
| Node Classification | LastFM | 21 | Mar 24, 2026 | ||
| Mathematical Reasoning | AIME 24 | 21 | Jun 9, 2026 | ||
| Inverse problem | Poisson | 21 | Feb 26, 2026 | ||
| Unverbalized Bias Detection | Hiring Task | 21 | Feb 26, 2026 | ||
| Mathematical Reasoning | OlympiadBench | 21 | Mar 10, 2026 |