Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 350 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Jailbreaking | JailbreakBench | 53 | May 6, 2026 | ||
| PDE solving | Poisson 2D (test) | 53 | Jun 25, 2026 | ||
| Mortality Prediction | eICU | 53 | May 12, 2026 | ||
| Knowledge Tracing | Assistments 2009 | 53 | May 12, 2026 | ||
| Infrared Small Target Detection | SIRST3 (test) | 53 | May 15, 2026 | ||
| Visual Search | V* | 53 | Jun 30, 2026 | ||
| NC vs. MCI classification | ADNI | 53 | Jun 19, 2026 | ||
| Text-to-image generation | HPD v2 (test) | 53 | Jun 11, 2026 | ||
| Document Visual Question Answering | SlideVQA | 53 | May 15, 2026 | ||
| Diagnostic Classification | UBC-OCEAN | 53 | Mar 24, 2026 | ||
| Camera pose estimation | YFCC100M Known Scene | 53 | Jun 4, 2026 | ||
| Virtual Staining | MIST HER2 | 53 | Jun 11, 2026 | ||
| Video Multimodal Understanding | VideoMMMU | 53 | May 28, 2026 | ||
| Novel View Synthesis | DeepBlending (test) | 53 | Jun 9, 2026 | ||
| Mortality Prediction | MIMIC-IV | 53 | Jun 30, 2026 | ||
| Visual Question Answering | OCRBench | 53 | Jul 7, 2026 | ||
| Language Understanding | Polish Open Leaderboard | 53 | Apr 14, 2026 | ||
| Downstream Performance Evaluation | CORE | 53 | May 22, 2026 | ||
| Optimization Modeling | NL4Opt | 53 | Apr 23, 2026 | ||
| Multi-Hop Question Answering | HotpotQA in-domain | 53 | Jun 9, 2026 | ||
| Irregular Time-Series Classification | E-MNIST | 53 | May 7, 2026 | ||
| Mathematical reasoning | MathVision (test) | 53 | Mar 16, 2026 | ||
| Reasoning | GPQA-D | 53 | May 12, 2026 | ||
| Spatial Reasoning | OmniSpatial (test) | 53 | Mar 4, 2026 | ||
| Red-teaming Safety Evaluation | StrongReject | 53 | Apr 23, 2026 |