Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1565 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Hallucination Evaluation | CHAIR (test) | 20 | May 12, 2026 | ||
| Object Segmentation | TrashCan | 20 | May 12, 2026 | ||
| Novel view interpolation | Dynamic Object Dataset | 20 | May 12, 2026 | ||
| Contextual Integrity Reasoning | PrivacyLens | 20 | May 12, 2026 | ||
| Formula translation complexity analysis | Temporal Logic Requirement Patterns past semantics | 20 | May 12, 2026 | ||
| MTL Formula Complexity Analysis | Fretish Requirement Patterns Finite Semantics | 20 | May 12, 2026 | ||
| Dense Image Generation | Unifybench++ | 20 | May 12, 2026 | ||
| Image Classification | PCam | 20 | May 12, 2026 | ||
| Image Classification | MHIST | 20 | May 12, 2026 | ||
| Image Classification | CRC100k | 20 | May 12, 2026 | ||
| Report Generation | MIMIC | 20 | May 12, 2026 | ||
| Report Generation | IU-XRay | 20 | May 12, 2026 | ||
| Multiple-Choice Question Answering | MIMIC | 20 | May 12, 2026 | ||
| Multiple-Choice Question Answering | IU-XRay | 20 | May 12, 2026 | ||
| True/False Question Answering | MIMIC | 20 | May 12, 2026 | ||
| True/False Question Answering | IU-XRay | 20 | May 12, 2026 | ||
| Open-vocabulary detection | LVIS OV (val) | 20 | May 12, 2026 | ||
| Sequential environment decision making | Crafter BALROG protocol | 20 | Jul 2, 2026 | ||
| Interaction Type Prediction | SHS148k (BFS) | 20 | May 12, 2026 | ||
| Interaction Type Prediction | SHS148k (DFS) | 20 | May 12, 2026 | ||
| Interaction Type Prediction | SHS148k Random | 20 | May 12, 2026 | ||
| Interaction Type Prediction | SHS27k (BFS) | 20 | May 12, 2026 | ||
| Interaction Type Prediction | SHS27k (DFS) | 20 | May 12, 2026 | ||
| Interaction Type Prediction | SHS27k (Random) | 20 | May 12, 2026 | ||
| Toxicity Detection | CivilComments BERT (test) | 20 | May 12, 2026 |