Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 217 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Relation Extraction | ACE05 (test) | 72 | Feb 26, 2026 | ||
| Multi-label Image Classification | VOC 2012 (test) | 72 | Mar 5, 2026 | ||
| Student Simulation | Java 5 | 72 | Feb 26, 2026 | ||
| Solution Simulation | Student_15 1.0 (test) | 72 | Feb 26, 2026 | ||
| Student behavior and solution simulation | Student_100 1.0 (full) | 72 | Feb 26, 2026 | ||
| Solution Simulation | Student 100 1.0 (test) | 72 | Feb 26, 2026 | ||
| Student Simulation | C++_5 | 72 | Feb 26, 2026 | ||
| Transductive Node Classification | Cora (transductive) | 72 | Feb 26, 2026 | ||
| Action Recognition | NTU-120 110/10 split | 72 | Apr 21, 2026 | ||
| Visual Place Recognition | Nordland | 72 | Feb 26, 2026 | ||
| Anomaly Classification | LiverCT | 72 | Feb 26, 2026 | ||
| Face Alignment | COFW (test) | 72 | Feb 26, 2026 | ||
| Long-horizon task completion | Calvin ABC->D | 72 | Jul 9, 2026 | ||
| Question Answering | Natural Question (NQ) (dev) | 72 | Feb 26, 2026 | ||
| Instance Segmentation | ScanNet200 (val) | 72 | Mar 27, 2026 | ||
| Image Classification | ImageNet-1K (test) | 71 | Jul 9, 2026 | ||
| Mathematical Reasoning | DART-Math DM-1 | 71 | Jun 8, 2026 | ||
| Mathematical Reasoning | SVAMP | 71 | Jul 2, 2026 | ||
| CNOT circuit synthesis | Matrices used in block ciphers | 71 | May 26, 2026 | ||
| Reasoning | LiveCodeBench | 71 | Jun 18, 2026 | ||
| Visual Question Answering | M3CoT | 71 | May 26, 2026 | ||
| Mathematical Reasoning | AMC 23 | 71 | Jun 9, 2026 | ||
| Question Answering | TriviaQA | 71 | May 11, 2026 | ||
| Membership Inference Attack | Flickr | 71 | Apr 2, 2026 | ||
| Object Hallucination Evaluation | MSCOCO POPE | 71 | Jun 1, 2026 |