Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1614 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Learning to Defer | CIFAR-100 varying-accuracy synthetic expert (test) | 20 | Feb 26, 2026 | ||
| Learning to Defer | ImageNet Overlapped Dog Expert | 20 | Feb 26, 2026 | ||
| Learning to Defer | ImageNet Dog Expert | 20 | Feb 26, 2026 | ||
| Learning to Defer | CIFAR-100 Overlapped Animal Expert | 20 | Feb 26, 2026 | ||
| Learning to Defer | CIFAR-100 Animal Expert | 20 | Feb 26, 2026 | ||
| Physical space generation | Vorticity and Convection Physical Simulation | 20 | Feb 26, 2026 | ||
| Knowledge Graph Retrieval | STaRK-Prime Synthetic 1.0 | 20 | Feb 26, 2026 | ||
| Knowledge Graph Retrieval | STaRK-MAG Synthetic 1.0 | 20 | Feb 26, 2026 | ||
| Knowledge Graph Retrieval | STaRK-Amazon Synthetic 1.0 | 20 | Feb 26, 2026 | ||
| Retrieval | STaRK PRIME Synthetic | 20 | Feb 26, 2026 | ||
| Retrieval | STaRK MAG Synthetic | 20 | Feb 26, 2026 | ||
| Retrieval | STaRK AMAZON Synthetic | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | BRUMO | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | HMMT | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME 24 | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME 25 | 20 | Feb 26, 2026 | ||
| Question Answering | GPQA | 20 | Feb 26, 2026 | ||
| Reasoning | Brumo 25 | 20 | Feb 26, 2026 | ||
| Reasoning | HMMT Feb 25 | 20 | Feb 26, 2026 | ||
| Reasoning | AIME 25 | 20 | Feb 26, 2026 | ||
| Quantitative Phase Imaging | Clinical urine microscopy through-focus brightfield images | 20 | Feb 26, 2026 | ||
| Click Prediction | RecGaze 1.0 (test) | 20 | Feb 26, 2026 | ||
| Illicit task completion | AgentHarm English prompts | 20 | Feb 26, 2026 | ||
| Domain Adaptation | BioASQ (test) | 20 | Feb 26, 2026 | ||
| Domain Adaptation | KUP (test) | 20 | Feb 26, 2026 |