Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1166 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Data Leakage Attack | Fin | 24 | Jun 15, 2026 | ||
| Recommendation | Yelp | 24 | Jun 15, 2026 | ||
| Recommendation | Amazon-Book | 24 | Jun 15, 2026 | ||
| Recommendation | MovieLens | 24 | Jun 15, 2026 | ||
| Semantic Similarity | MRPC (test) | 24 | Jun 15, 2026 | ||
| Image Classification | CIFAR-10 (test) | 24 | Jun 15, 2026 | ||
| Multi-domain Evaluation | Diverse Domain Collection (MATH, GSM-H, AQUA, AIME, SciBe, GPQA, MMLUP, MedMC, HEval, MBPP) | 24 | Jun 15, 2026 | ||
| Science | SciBench | 24 | Jun 15, 2026 | ||
| Optimal Subgroup Identification | eICU ventilation-free days within 7 days (test) | 24 | Jun 15, 2026 | ||
| Subgroup Identification | eICU ventilation-free-days outcome | 24 | Jun 15, 2026 | ||
| Question Answering | MedQA | 24 | Jun 12, 2026 | ||
| Question Answering | ARC-Challenge | 24 | Jun 12, 2026 | ||
| Overall Spreadsheet Performance | SpreadsheetBench and WikiTableQuestions Combined | 24 | Jun 12, 2026 | ||
| Out-of-Distribution Table Question Answering | WikiTableQuestions (WikiTQ) | 24 | Jun 12, 2026 | ||
| Spreadsheet Task Execution | SpreadsheetBench Full | 24 | Jun 12, 2026 | ||
| Spreadsheet Task Execution | SpreadsheetBench Verified (Held-out) | 24 | Jun 12, 2026 | ||
| Time-series Forecasting | COVID-19 79 regions | 24 | Jun 12, 2026 | ||
| Equilibrium State Estimation | COVID-19 (test) | 24 | Jun 12, 2026 | ||
| Bilingual Response Generation | Chinese zh | 24 | Jun 12, 2026 | ||
| Bilingual Response Generation | English en | 24 | Jun 12, 2026 | ||
| pick toy | Real-World Robot Experiments v1 (test) | 24 | Jun 12, 2026 | ||
| Intrusion Detection | BoT-IoT (test) | 24 | Jun 12, 2026 | ||
| Continual Learning | Split CIFAR-10 | 24 | Jun 23, 2026 | ||
| Multicalibration | Bank Marketing | 24 | Jun 12, 2026 | ||
| Question Answering | TriviaQA | 24 | Jun 11, 2026 |