Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1865 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | MNIST | 18 | Mar 30, 2026 | ||
| Image Classification | GTSRB | 18 | Mar 30, 2026 | ||
| Multi-task Sequence Performance | CityScapes | 18 | Mar 30, 2026 | ||
| 7-class Semantic Segmentation | CityScapes | 18 | Mar 30, 2026 | ||
| Depth Estimation | Taskonomy | 18 | Mar 30, 2026 | ||
| Clinical Decision Making | MedChain (overall) | 18 | Mar 30, 2026 | ||
| Medical Question Answering | MedQA US (test) | 18 | Mar 30, 2026 | ||
| Medical Visual Question Answering | SLAKE-CP | 18 | Apr 23, 2026 | ||
| Video Multimodal Understanding | MMVU | 18 | Jun 12, 2026 | ||
| Symbolic Regression | SRBench known solutions 10% noise | 18 | Mar 30, 2026 | ||
| Symbolic Regression | SRBench known solutions 1% noise | 18 | Mar 30, 2026 | ||
| Symbolic Regression | SRBench known solutions 0.1% noise | 18 | Mar 30, 2026 | ||
| Symbolic Regression | SRBench known solutions 0.0% noise | 18 | Mar 30, 2026 | ||
| Zero-shot Reasoning | Reasoning Tasks (PIQA, ARC-e, HS, WG) Zero-shot | 18 | Mar 27, 2026 | ||
| Foreground Extraction | CDnet Highway | 18 | Mar 27, 2026 | ||
| Autonomous Driving | LaMPilot-Bench | 18 | Mar 27, 2026 | ||
| Multi-modal Reasoning | NuPlanQA EVAL | 18 | Mar 27, 2026 | ||
| Machine Translation | German-to-English (test) | 18 | Mar 27, 2026 | ||
| Long-Horizon Search Intelligence | BrowseComp-zh | 18 | Mar 27, 2026 | ||
| Long-Horizon Search Intelligence | GAIA | 18 | Mar 27, 2026 | ||
| Fact Verification | FEVER | 18 | Mar 27, 2026 | ||
| Binary Lesion Classification | Colon-Bench | 18 | Mar 27, 2026 | ||
| Precipitation Forecasting | Ban Nhung Basin | 18 | Mar 27, 2026 | ||
| Molecular Property Prediction | QM9 | 18 | Mar 27, 2026 | ||
| Neuron Interpretation | ImageNet 1K (val) | 18 | Mar 27, 2026 |