Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1017 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | AMC 23 | 27 | Mar 6, 2026 | ||
| Anomaly Detection | MSL | 27 | Jun 2, 2026 | ||
| Image Classification | CIFAR-10 | 27 | Feb 26, 2026 | ||
| Machine Unlearning | CIFAR-10 Random Forget (50%) | 27 | Jun 2, 2026 | ||
| Long-context understanding | RULER 128K | 27 | May 19, 2026 | ||
| Language Modeling | C4 Qwen2.5 (val) | 27 | Feb 26, 2026 | ||
| Classification | Adult | 27 | Mar 27, 2026 | ||
| Agent Task Completion | ToolSandbox (test) | 27 | Feb 26, 2026 | ||
| Agent Task Completion | τ2-BENCH (test) | 27 | Feb 26, 2026 | ||
| Agent Task Completion | τ-BENCH (test) | 27 | Feb 26, 2026 | ||
| Treatment Effect Estimation | IHDP | 27 | Apr 7, 2026 | ||
| Trust Prediction | Epinions 1.0 (unobserved users) | 27 | Feb 26, 2026 | ||
| Trust Prediction | Epinions 1.0 (observed users) | 27 | Feb 26, 2026 | ||
| Six-class classification of EEG events | TUEV | 27 | May 1, 2026 | ||
| Confidence Calibration | SimpleQA | 27 | Feb 26, 2026 | ||
| Jailbreaking Attack | AdvBench | 27 | Mar 4, 2026 | ||
| Code Generation | MBPP | 27 | Mar 17, 2026 | ||
| Time Series Forecasting | WTH | 27 | Feb 26, 2026 | ||
| Time Series Forecasting | ETTm1 | 27 | Feb 26, 2026 | ||
| Node Classification | Cora | 27 | Mar 5, 2026 | ||
| Time Series Forecasting | ETTh1 (test) | 27 | May 19, 2026 | ||
| Backdoor Defense | GTSRB 1% poison rate (test) | 27 | Feb 26, 2026 | ||
| Clustering | AC | 27 | Mar 6, 2026 | ||
| Question Answering | GPQA Diamond | 27 | Feb 26, 2026 | ||
| Math problem solving | GSM8K | 27 | Feb 26, 2026 |