Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1526 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| General Knowledge Reasoning | MMLU College | 20 | Jul 7, 2026 | ||
| General Knowledge Reasoning | MMLU High | 20 | Jul 7, 2026 | ||
| Scientific Question Answering | SciEval Static | 20 | Jul 7, 2026 | ||
| Jailbreak Defense | Dictionary-based Jailbreak Evaluation | 20 | Jul 7, 2026 | ||
| Helpfulness Evaluation | Alpaca | 20 | Jul 7, 2026 | ||
| Jailbreak Attack Evaluation | DeepIn | 20 | Jul 7, 2026 | ||
| Jailbreak Attack Evaluation | GPTFuzz | 20 | Jul 7, 2026 | ||
| Patient drug response prediction | TCGA Patient split | 20 | Jul 7, 2026 | ||
| Tool Use | Aggregate Performance | 20 | Jul 7, 2026 | ||
| Tool Use | LiveMCPBench | 20 | Jul 7, 2026 | ||
| Tool Use | BFCL | 20 | Jul 7, 2026 | ||
| Watermark detection | MMW | 20 | Jul 7, 2026 | ||
| Watermark detection | ptb-text | 20 | Jul 7, 2026 | ||
| Watermark detection | Wiki-103 | 20 | Jul 7, 2026 | ||
| Jailbreak Attack | Harmful instructions | 20 | Jul 7, 2026 | ||
| Molecule Property Prediction | DrugOOD-EC50 (scaffold) | 20 | Jul 7, 2026 | ||
| Molecule Property Prediction | DrugOOD-IC50 (scaffold) | 20 | Jul 7, 2026 | ||
| Depression Detection | E-DAIC (test) | 20 | Jul 7, 2026 | ||
| Depression Detection | MODMA (test) | 20 | Jul 7, 2026 | ||
| Attack Detection Robustness | TON_IoT | 20 | Jul 7, 2026 | ||
| Attack Detection Robustness | UNSW15 | 20 | Jul 7, 2026 | ||
| Spatial Reasoning | SpatialReasonerEval | 20 | Jul 7, 2026 | ||
| Spatial Navigation | Spatial Navigation (OOD) | 20 | Jul 3, 2026 | ||
| Spatial Navigation | Spatial Navigation (ID) | 20 | Jul 3, 2026 | ||
| Semantic Segmentation | Vaihingen CR-thick | 20 | Jul 3, 2026 |