Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 850 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Sales interaction performance | SalesLLM EN 1.0 | 30 | Apr 10, 2026 | ||
| Traveling Salesman Problem | Uniform Euclidean TSP n = 500 | 30 | Jun 9, 2026 | ||
| Math reasoning | GSM-Hard (test) | 30 | Apr 10, 2026 | ||
| General language understanding and reasoning | Huggingface Open LLM Leaderboard | 30 | May 26, 2026 | ||
| Image Retrieval | Curated-5K (test) | 30 | Apr 9, 2026 | ||
| Scale-Invariant Depth Estimation | Bonn | 30 | Apr 9, 2026 | ||
| Jailbreaking | EHRAgent TREQS | 30 | Apr 8, 2026 | ||
| Jailbreaking | EHRAgent eICU | 30 | Apr 8, 2026 | ||
| Jailbreaking | EHRAgent MIMIC-III | 30 | Apr 8, 2026 | ||
| Knowledge Editing | WikiUpdate | 30 | Apr 8, 2026 | ||
| Knowledge Editing | Counterfact uns | 30 | Apr 8, 2026 | ||
| Knowledge Editing | MQuAKE | 30 | May 19, 2026 | ||
| Attack Success Rate Evaluation | SKILL-INJECT Contextual | 30 | Apr 8, 2026 | ||
| Attack Success Rate Evaluation | SKILL-INJECT Obvious | 30 | Apr 8, 2026 | ||
| Real-world Visual Understanding | RealWorldQA (test) | 30 | Jun 12, 2026 | ||
| Free-rider Detection | MNIST IID Scenario 1 | 30 | Apr 7, 2026 | ||
| Language Modeling | Medical (Med) | 30 | Apr 7, 2026 | ||
| Image Classification | STL10 | 30 | Jun 12, 2026 | ||
| Molecular Energy Prediction | QM9 (test) | 30 | Apr 7, 2026 | ||
| Information Retrieval | MAIR 20% labeled query-document pairs | 30 | Apr 7, 2026 | ||
| Image Retrieval | FLICKR25K | 30 | Apr 7, 2026 | ||
| Image Retrieval | CIFAR10 | 30 | Apr 7, 2026 | ||
| Bivariate Causal Discovery | LS-s | 30 | Apr 8, 2026 | ||
| Force tracking | 14 Experimental Objects Grasping Experiment | 30 | Apr 7, 2026 | ||
| Membership Inference Attack | AG News, WikiText-103, XSum, and Swallow-Code (held-out) | 30 | Apr 6, 2026 |