Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1622 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Hurst estimation | fBm (test) | 20 | Feb 26, 2026 | ||
| Classification | Synthetic Manifolds OOD (test) | 20 | Feb 26, 2026 | ||
| Classification | Synthetic Manifolds ID (test) | 20 | Feb 26, 2026 | ||
| Language Model Pre-training | C4 Llama-160M scratch (val) | 20 | Feb 26, 2026 | ||
| Robustness Evaluation | MultiRLVR | 20 | Feb 26, 2026 | ||
| Robustness Evaluation | MATH | 20 | Feb 26, 2026 | ||
| Robustness Evaluation | GSM8K | 20 | Feb 26, 2026 | ||
| Robustness Evaluation | AIME | 20 | Feb 26, 2026 | ||
| Outlier Detection | Optdigits | 20 | Mar 16, 2026 | ||
| Mathematical Reasoning | AIME 2024-2025 | 20 | Apr 21, 2026 | ||
| Summarization | Summarize from Feedback (test) | 20 | Feb 26, 2026 | ||
| MapIdTransform | MapIdTransform workload | 20 | Feb 26, 2026 | ||
| Time Series Forecasting | Exchange | 20 | Feb 26, 2026 | ||
| Time Series Forecasting | Weather | 20 | Feb 26, 2026 | ||
| Time Series Forecasting | ETTh1 | 20 | Feb 26, 2026 | ||
| Time Series Forecasting | ETTm2 | 20 | Feb 26, 2026 | ||
| Time Series Forecasting | ETTm1 | 20 | Feb 26, 2026 | ||
| Tool selection | ToolAlpaca | 20 | Feb 26, 2026 | ||
| Tool selection | API-Bench | 20 | Feb 26, 2026 | ||
| Tool selection | SD Single-domain | 20 | Feb 26, 2026 | ||
| Tool selection | CD Cross-domain | 20 | Feb 26, 2026 | ||
| White Matter Tractography | HCP (Human Connectome Project) (test) | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | AMO-Bench | 20 | Apr 15, 2026 | ||
| Question Answering | SQuAD 50-passage (train) | 20 | Feb 26, 2026 | ||
| Question Answering | SQuAD 200-passage (val) | 20 | Feb 26, 2026 |