Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 669 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Conformal Prediction | VentricularVolume (OUT) | 35 | Jul 7, 2026 | ||
| Salient Object Detection | ORSI-4199 2022 (test) | 35 | Jul 7, 2026 | ||
| Lexical Retrieval | HotpotQA | 35 | Jul 3, 2026 | ||
| Lexical Retrieval | MS MARCO | 35 | Jul 3, 2026 | ||
| Lexical Retrieval | Natural Questions | 35 | Jul 3, 2026 | ||
| Generalization Evaluation | AM-Thinking Distilled-math&code v1 (Unseen) | 35 | Jul 2, 2026 | ||
| Language Model Evaluation | Tulu-3 (dev) | 35 | Jul 2, 2026 | ||
| Robust Pose Graph Optimization | 2D SLAM datasets (Intel, Csail, FR079, FRH) (outlier ratio sets) | 35 | Jun 30, 2026 | ||
| Provenance Tracing | Infinity | 35 | Jun 30, 2026 | ||
| Provenance Tracing | VAR | 35 | Jun 30, 2026 | ||
| Provenance Tracing | Taming | 35 | Jun 30, 2026 | ||
| Provenance Tracing | LlamaGen | 35 | Jun 30, 2026 | ||
| Image Classification | MURA Fracture | 35 | Jun 30, 2026 | ||
| QDA classification | Neural data | 35 | Jun 29, 2026 | ||
| KNN classification | Zand-Kohn | 35 | Jun 29, 2026 | ||
| Multiframe Infrared Small Target Detection | NUDT-MIRSDT Hard subset | 35 | Jun 29, 2026 | ||
| Multiframe Infrared Small Target Detection | NUDT-MIRSDT (All) | 35 | Jun 29, 2026 | ||
| Semantic Uncertainty Stability Prediction | BBEH | 35 | Jun 29, 2026 | ||
| Causality | BBEH | 35 | Jun 29, 2026 | ||
| Minimality Evaluation | BBEH (test) | 35 | Jun 29, 2026 | ||
| Same-task discrimination accuracy | BBEH | 35 | Jun 29, 2026 | ||
| Text-to-Image Generation | FLUX.1 DrawBench dev 1.0 (test) | 35 | Jun 26, 2026 | ||
| Commonsense Reasoning | Commonsense Reasoning Suite (PIQA, ARC-e, ARC-c, HellaSwag, WinoGrande) | 35 | Jun 30, 2026 | ||
| AUC of the ET inspector | US Income CA14 | 35 | Jun 26, 2026 | ||
| Object Detection | CARPK (test) | 35 | Jun 25, 2026 |