Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 729 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Variable Tracking | RULER-VT | 33 | Mar 12, 2026 | ||
| Key-value Retrieval | LITM (Lost in the Middle) | 33 | Mar 12, 2026 | ||
| Graph Anomaly Detection | Yelp | 33 | May 13, 2026 | ||
| Text Retrieval | MSCOCO | 33 | Mar 6, 2026 | ||
| Image Denoising | BSD68 | 33 | May 13, 2026 | ||
| Instruction Following | Instruction-Following (val) | 33 | Mar 5, 2026 | ||
| Honesty Alignment | Natural Questions (NQ) In-Domain | 33 | Mar 5, 2026 | ||
| Visual Question Answering | NuscenesQA | 33 | May 1, 2026 | ||
| Document Extraction | Dataset C2 Finance domain (test) | 33 | Mar 4, 2026 | ||
| Document Extraction | Dataset C1 Supply chain domain (test) | 33 | Mar 4, 2026 | ||
| Pedagogical Response Evaluation | KMP-Dialogue | 33 | Mar 4, 2026 | ||
| Information Retrieval | NFCorpus | 33 | Apr 20, 2026 | ||
| Stereo Matching | Booster Q | 33 | Apr 13, 2026 | ||
| Verilog Code Generation | VerilogEval CC v2 | 33 | Mar 4, 2026 | ||
| Correctness Prediction | GSM8K | 33 | May 11, 2026 | ||
| Proficiency estimation | EgoExo4D Ego+Exos view | 33 | Jun 17, 2026 | ||
| Proficiency estimation | EgoExo4D Exos view | 33 | Jun 17, 2026 | ||
| Proficiency estimation | EgoExo4D Ego view | 33 | Jun 17, 2026 | ||
| Anomaly Generation | MVTec-AD (test) | 33 | Apr 10, 2026 | ||
| Object Detection | VOC7+12 (val) | 33 | Mar 4, 2026 | ||
| Malicious behavior measurement | AgentHarm Harmful | 33 | May 8, 2026 | ||
| Short-term forecasting | EPF BE | 33 | Mar 26, 2026 | ||
| Short-term forecasting | EPF PJM | 33 | Mar 26, 2026 | ||
| Image Classification | MNIST LQ-3 partition (test) | 33 | Feb 27, 2026 | ||
| Image Classification | MNIST LQ-2 partition (test) | 33 | Feb 27, 2026 |