Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1795 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Model Merging | 8 Vision Tasks (average) | 18 | Jun 18, 2026 | ||
| Anomaly detection | Stack | 18 | Jun 18, 2026 | ||
| Anomaly detection | HM | 18 | Jun 18, 2026 | ||
| Anomaly detection | Avito | 18 | Jun 18, 2026 | ||
| Anomaly detection | ArXiv | 18 | Jun 18, 2026 | ||
| Lithium Mining Production Planning | Historical Lithium Price Data | 18 | Jun 18, 2026 | ||
| Lithium mining policy optimization | Lithium prices planned with GBM alpha = 0.5 (historical) | 18 | Jun 18, 2026 | ||
| 3D Place Recognition | CS-Campus3D | 18 | Jun 18, 2026 | ||
| Retrieval | CS-Urban-Scenes (test) | 18 | Jun 18, 2026 | ||
| Grounded ECG Interpretation | GEM (test) | 18 | Jun 18, 2026 | ||
| Hallucination Detection | GSM8k | 18 | Jun 19, 2026 | ||
| cash-management | ten-account cash-management (val) | 18 | Jun 18, 2026 | ||
| Multilingual Code Generation | MultiPL-E | 18 | Jun 17, 2026 | ||
| Code Generation | HumanEval+ | 18 | Jun 17, 2026 | ||
| Sudoku Solving | Sudoku 25x25 (90% masking) | 18 | Jun 17, 2026 | ||
| Sudoku Solving | Sudoku 25x25 80% masking | 18 | Jun 17, 2026 | ||
| Sudoku Solving | Sudoku 25x25 70% masking | 18 | Jun 17, 2026 | ||
| Node Classification | Coauthor-CS | 18 | Jun 23, 2026 | ||
| Image Classification | Tiny-ImageNet (test) | 18 | Jun 17, 2026 | ||
| Video Classification | EV9V (test) | 18 | Jun 17, 2026 | ||
| Video Classification | EV9V (val) | 18 | Jun 17, 2026 | ||
| Open-Web Reasoning | GAIA Open-web via SERPER (test) | 18 | Jun 17, 2026 | ||
| Pitch Style Conversion | VocalSet and GTSinger | 18 | Jun 17, 2026 | ||
| Secret data extraction attack | FedLLM 100 target secrets | 18 | Jun 17, 2026 | ||
| Secret Data Extraction | 100 Targeted Secrets OKVQA DocVQA VQAv2 | 18 | Jun 17, 2026 |