Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1169 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | AMOBench | 24 | Jun 9, 2026 | ||
| Code Generation | HumanEval+ | 24 | Jun 9, 2026 | ||
| Malicious Fine-tuning Attack | HEx-PHI | 24 | Jun 30, 2026 | ||
| Attack success evaluation | Beavertails | 24 | Jun 9, 2026 | ||
| Visual Reasoning | VisualFLIP | 24 | Jun 9, 2026 | ||
| Linear bandit | Linear bandit setting ε = 0.4, B = 3 (test) | 24 | Jun 9, 2026 | ||
| Yield prediction | dataset 2023 (val) | 24 | Jun 9, 2026 | ||
| Cold-start Photovoltaic Forecasting | 440 Photovoltaic Sites PVGIS context (cold-start evaluation) | 24 | Jun 8, 2026 | ||
| Cold-start Photovoltaic Forecasting | 440 Photovoltaic Sites OPAQUE context (cold-start evaluation) | 24 | Jun 8, 2026 | ||
| Photovoltaic Forecasting | PVGIS context synthetic (full 440-site grid) | 24 | Jun 8, 2026 | ||
| Photovoltaic Forecasting | OPAQUE context synthetic (full 440-site grid) | 24 | Jun 8, 2026 | ||
| Photovoltaic Forecasting | PVGIS context | 24 | Jun 8, 2026 | ||
| Photovoltaic Forecasting | OPAQUE context | 24 | Jun 8, 2026 | ||
| Spatial Reasoning | CV-3D | 24 | Jun 8, 2026 | ||
| Social Dimension Classification | P1SCO Perspectivist N=1104 (test) | 24 | Jun 8, 2026 | ||
| Social Dimension Classification | P1SCO Majority N=1104 (test) | 24 | Jun 8, 2026 | ||
| Spatiotemporal Imputation | PeMS08 (test) | 24 | Jun 8, 2026 | ||
| Model Stealing | ACM G (test) | 24 | Jun 8, 2026 | ||
| Surrogate Node Classification | Pubmed G (test) | 24 | Jun 8, 2026 | ||
| Model Extraction | Citeseer G (test) | 24 | Jun 8, 2026 | ||
| Entity-conditioned retrieval | Chest X-ray (External) | 24 | Jun 5, 2026 | ||
| Video Question Answering | StoryVideoQA-G 1.0 (gold) | 24 | Jun 5, 2026 | ||
| Cloud Removal | RICE2 (test) | 24 | Jun 5, 2026 | ||
| Text-to-audio retrieval | CLOTHO v1 (test) | 24 | Jun 5, 2026 | ||
| Mathematical Reasoning | AQuA | 24 | Jun 5, 2026 |