Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1611 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Symbolic Regression | Feynman Dataset epsilon=0.1 (test) | 20 | Feb 26, 2026 | ||
| Symbolic Regression | Strogatz Dataset epsilon=0.1 (test) | 20 | Feb 26, 2026 | ||
| Symbolic Regression | Feynman Dataset epsilon=0.01 (test) | 20 | Feb 26, 2026 | ||
| Symbolic Regression | Strogatz Dataset epsilon=0.01 (test) | 20 | Feb 26, 2026 | ||
| Symbolic Regression | Feynman Dataset epsilon=0.001 (test) | 20 | Feb 26, 2026 | ||
| Symbolic Regression | Strogatz Dataset epsilon=0.001 (test) | 20 | Feb 26, 2026 | ||
| Image Generation | FLUX-1 (dev) | 20 | May 25, 2026 | ||
| Long-context Input (Summarization) | BookSum | 20 | Feb 27, 2026 | ||
| Long-context Generation (Reasoning) | MMLU-Pro | 20 | Feb 27, 2026 | ||
| Long-context Generation (Reasoning) | AIME25 | 20 | Feb 27, 2026 | ||
| Long-context Generation (Reasoning) | AIME24 | 20 | Feb 27, 2026 | ||
| Multi-class classification | New-thyroid | 20 | Feb 26, 2026 | ||
| Multi-class classification | Balance | 20 | Feb 26, 2026 | ||
| Multi-class classification | Yeast | 20 | Mar 18, 2026 | ||
| Multi-class classification | Vehicle | 20 | Feb 26, 2026 | ||
| Hybrid Retrieval-Augmented Generation | Hybrid RAG | 20 | Feb 26, 2026 | ||
| 3DGS Compression | Mip-NeRF360 | 20 | May 21, 2026 | ||
| End-to-End Performance | Clipper | 20 | Feb 27, 2026 | ||
| End-to-End Performance | LongMemEval | 20 | Feb 27, 2026 | ||
| HDR Reconstruction | HDR-Eye | 20 | Feb 26, 2026 | ||
| HDR Reconstruction | VDS | 20 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 Dirichlet-0.05 (test) | 20 | Feb 26, 2026 | ||
| Time Series Forecasting | TimeMMD Traffic (test) | 20 | May 29, 2026 | ||
| Time Series Forecasting | TimeMMD Social Good (test) | 20 | May 29, 2026 | ||
| Time Series Forecasting | TimeMMD Security (test) | 20 | May 29, 2026 |