Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 379 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| User Repeat Prediction | Rel Event | 50 | Apr 1, 2026 | ||
| User Ignore Prediction | Rel Event | 50 | Apr 1, 2026 | ||
| Image Captioning | POPE Adversarial | 50 | Mar 5, 2026 | ||
| Automated Interpretability Evaluation | Gemma-2-2B | 50 | Jun 15, 2026 | ||
| Contact Estimation | Mixed (test) | 50 | Mar 4, 2026 | ||
| Information Retrieval | COVID | 50 | May 11, 2026 | ||
| General Knowledge Question Answering | MMLU | 50 | May 26, 2026 | ||
| Paper-to-code synthesis | NERFIFY-BENCH 10 NeRF Papers 1.0 | 50 | Mar 4, 2026 | ||
| Robustness verification | Iris | 50 | Mar 4, 2026 | ||
| Robustness Verification | Iris Sigmoid Network | 50 | Mar 4, 2026 | ||
| Sequential Recommendation | Amazon Arts (test) | 50 | Mar 4, 2026 | ||
| Privacy Editing | TDE URL | 50 | Feb 27, 2026 | ||
| Sequential Recommendation | gowalla | 50 | May 21, 2026 | ||
| Forecasting | ETT1 (test) | 50 | Feb 26, 2026 | ||
| Arithmetic Reasoning | In-domain (test) | 50 | Feb 26, 2026 | ||
| Table Question Answering | HiTab | 50 | Feb 26, 2026 | ||
| Table Question Answering | SequentialQA | 50 | Feb 26, 2026 | ||
| Table Question Answering | WikiTQ | 50 | Feb 26, 2026 | ||
| Generalized Category Discovery | Oxford Pets | 50 | Mar 17, 2026 | ||
| Safety Evaluation | WildJailbreak (held-out) | 50 | Feb 26, 2026 | ||
| Molecular graph generation | QM9 | 50 | Jun 4, 2026 | ||
| Object Hallucination in Open-ended Captioning | CHAIR (test) | 50 | Mar 30, 2026 | ||
| Knowledge-Intensive Visual Question Answering | InfoSeek (val) | 50 | Apr 3, 2026 | ||
| Instruction Following | Dolly | 50 | May 21, 2026 | ||
| Deep Search | Browse Comp-ZH | 50 | Apr 15, 2026 |