Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1844 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Continuum Field Reconstruction | NSν1e-5 Avg | 18 | Apr 23, 2026 | ||
| Continuum Field Reconstruction | NS ν1e-5 (In-t) | 18 | Apr 23, 2026 | ||
| Continuum Field Reconstruction (Rollout) | 2D Navier-Stokes nu=1e-5 | 18 | Apr 23, 2026 | ||
| Web Browsing and Navigation | BrowseComp | 18 | Apr 23, 2026 | ||
| Image Forgery Detection | TRACE (test) | 18 | Apr 23, 2026 | ||
| Open-ended generation | Vicuna | 18 | Apr 23, 2026 | ||
| Open-ended generation | Dolly | 18 | Apr 23, 2026 | ||
| General Knowledge QA | superGPQA | 18 | Apr 23, 2026 | ||
| General Knowledge QA | MMLU-Pro | 18 | Apr 23, 2026 | ||
| General Knowledge QA | CSQA | 18 | Apr 23, 2026 | ||
| Math Reasoning | BigMath level 5 | 18 | Apr 23, 2026 | ||
| Math Reasoning | BigMath level 4 | 18 | Apr 23, 2026 | ||
| Employee Morale Prediction | Firm posts dataset Tmax, 15 posts threshold | 18 | Apr 23, 2026 | ||
| ROA Prediction | Firm posts dataset Tmax 15 posts threshold | 18 | Apr 23, 2026 | ||
| Object Hallucination Evaluation | POPE Concurrence | 18 | Apr 23, 2026 | ||
| Multiple Choice Question Answering | GPQA Diamond | 18 | Apr 21, 2026 | ||
| Time Series Forecasting | S&P 500 four time intervals ahead | 18 | Apr 21, 2026 | ||
| Time Series Forecasting | Cross rate four time intervals ahead | 18 | Apr 21, 2026 | ||
| Question Answering | HotPotQA | 18 | Apr 21, 2026 | ||
| Big-Bench Hard | BBH | 18 | Apr 21, 2026 | ||
| Defect Detection | CodeXGLUE Defect Detection (test) | 18 | Apr 21, 2026 | ||
| Clone Detection | CodeXGLUE Clone Detection | 18 | Apr 21, 2026 | ||
| Defect Detection | CodeXGLUE Defect Detection | 18 | Apr 21, 2026 | ||
| Multilingual Language Understanding | Qwen Multi-task Evaluation Suite 2.5 (test) | 18 | Apr 21, 2026 | ||
| Document Question Answering | DocVQA | 18 | May 13, 2026 |