Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 502 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| General Video Understanding | LVBench | 42 | Jul 2, 2026 | ||
| Hallucination Detection | MGSM | 42 | Apr 20, 2026 | ||
| Hallucination Detection | MedMCQA | 42 | Apr 20, 2026 | ||
| Hallucination Detection | SciQ | 42 | Apr 20, 2026 | ||
| Jailbreak Attack | Jailbreak-Bench | 42 | Apr 20, 2026 | ||
| Genomic sequence classification | Nucleotide Transformer Benchmark Human 500M (test) | 42 | Apr 16, 2026 | ||
| Visual Localization | Cambridge Landmarks St Mary’s Church | 42 | Apr 15, 2026 | ||
| Visual Localization | Cambridge Landmarks Shop Façade | 42 | Apr 15, 2026 | ||
| Visual Localization | Cambridge Landmarks King’s College | 42 | Apr 15, 2026 | ||
| Visual Localization | Cambridge Landmarks Great Court | 42 | Apr 15, 2026 | ||
| Sinogram endpoint estimation | PIS (test) | 42 | Apr 14, 2026 | ||
| Multiple Choice Question Answering | ConFiQA MC | 42 | Apr 14, 2026 | ||
| Faithfulness Evaluation | FaithEval | 42 | Apr 14, 2026 | ||
| Jailbreaking | StrongReject (test) | 42 | Jun 4, 2026 | ||
| EEG Classification | BNCI2014001, Weibo2014, BNCI2014002 Average | 42 | Apr 14, 2026 | ||
| EEG Classification | BNCI2014002 | 42 | Apr 14, 2026 | ||
| EEG Classification | Weibo 2014 | 42 | Apr 14, 2026 | ||
| EEG Classification | BNCI 2014001 | 42 | Apr 14, 2026 | ||
| Out-of-Distribution Detection | OpenImage-O (test) | 42 | May 11, 2026 | ||
| Out-of-Distribution Detection | NINCO (test) | 42 | May 11, 2026 | ||
| Image Manipulation Localization | CAT-Net (test) | 42 | Apr 13, 2026 | ||
| Time Series Forecasting | Noisy Almost Periodic Functions (test) | 42 | Apr 13, 2026 | ||
| Explaining LLMs | NQ | 42 | Apr 13, 2026 | ||
| Explaining LLMs | MMLU | 42 | Apr 13, 2026 | ||
| Explaining LLMs | SST | 42 | Apr 13, 2026 |