Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1534 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Clinical Trial Matching | TREC 2023 | 20 | Jun 23, 2026 | ||
| Clinical Trial Matching | TREC 2022 | 20 | Jun 23, 2026 | ||
| Clinical Trial Matching | TREC 2021 | 20 | Jun 23, 2026 | ||
| Image goal navigation | OGBench Cube | 20 | Jun 23, 2026 | ||
| Mathematical Reasoning | MATH500 | 20 | Jun 23, 2026 | ||
| Cross-view Temporal Reasoning | EgoExo-Con V-Exo | 20 | Jun 23, 2026 | ||
| Model Inversion | Celeb-A | 20 | Jun 23, 2026 | ||
| Multi-class sarcasm detection | Sarc7 | 20 | Jun 23, 2026 | ||
| 3D Semantic Segmentation | DAPS-3D 1.0 (test) | 20 | Jun 19, 2026 | ||
| 3D Semantic Segmentation | SemSTF 1.0 (test) | 20 | Jun 19, 2026 | ||
| 3D Semantic Segmentation | Rellis-3D 1.0 (test) | 20 | Jun 19, 2026 | ||
| 3D Semantic Segmentation | SemiKITTI 1.0 (test) | 20 | Jun 19, 2026 | ||
| Multiple Choice Questioning | RS-Neg MCQ (test) | 20 | Jun 19, 2026 | ||
| Visual Question Answering | RS-Neg VQA (test) | 20 | Jun 19, 2026 | ||
| Visual Question Answering | FloodNet | 20 | Jun 19, 2026 | ||
| Visual Grounding | RS-Neg | 20 | Jun 19, 2026 | ||
| Classification | RS-Neg | 20 | Jun 19, 2026 | ||
| Report-generation | DeepResearch Bench | 20 | Jun 19, 2026 | ||
| Time Series Anomaly Detection | TSB-AD-U (test) | 20 | Jun 19, 2026 | ||
| Arrhythmia Classification | PhysioNet Challenge Extreme Tachycardia ETC 2015 (test) | 20 | Jun 19, 2026 | ||
| Regression | BFP | 20 | Jun 19, 2026 | ||
| Ordinal Multiclass Classification | EOL | 20 | Jun 19, 2026 | ||
| Multiclass Classification | ESR | 20 | Jun 19, 2026 | ||
| Binary Classification | HFC | 20 | Jun 19, 2026 | ||
| Jailbreak Attack Defense | Adversarial Jailbreak Prompts | 20 | Jun 19, 2026 |