Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 653 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Machine-Generated Text Detection | Reuters (Claude) | 36 | Feb 26, 2026 | ||
| Machine-Generated Text Detection | Reuters GPT4All | 36 | Feb 26, 2026 | ||
| Mathematical Reasoning | CHAMP standard (test) | 36 | Feb 26, 2026 | ||
| Agent Performance | ACEBench Agent | 36 | Feb 26, 2026 | ||
| Question Answering | NarrativeQA | 36 | Feb 26, 2026 | ||
| Math | Math (test) | 36 | Feb 26, 2026 | ||
| Reasoning | Reasoning Benchmark Suite Aggregate | 36 | Mar 17, 2026 | ||
| Multimodal Science Question Answering | ScienceQA | 36 | Feb 26, 2026 | ||
| Legal Domain Fabrication and Factuality Analysis | JURIDICO-FCR 75 tasks | 36 | Feb 26, 2026 | ||
| Grid World Navigation | FrozenLake (Source) | 36 | Feb 26, 2026 | ||
| Issue Resolution | SWE-bench Verified (test) | 36 | Feb 26, 2026 | ||
| Embodied Task Completion | ALFRED EB | 36 | May 27, 2026 | ||
| Graph-to-Image | SemArt | 36 | Jul 1, 2026 | ||
| Multi-turn Medical Diagnosis | Med-Inquire DiagnosisArena (915 cases) | 36 | Feb 26, 2026 | ||
| Text Generation | 5 Generation tasks | 36 | Feb 26, 2026 | ||
| Concept Unlearning | UnlearnDiffAtk | 36 | Feb 26, 2026 | ||
| Mathematical Reasoning | OlympiadBench | 36 | Mar 4, 2026 | ||
| Phenotype prediction | MIMIC-IV | 36 | May 12, 2026 | ||
| Medical Visual Question Answering | PMC-VQA (test) | 36 | Mar 25, 2026 | ||
| Error Detection | ImageNet | 36 | May 26, 2026 | ||
| Tamper Localization | Columbia | 36 | Jun 24, 2026 | ||
| Road Scene | RoadSceneBench | 36 | Feb 26, 2026 | ||
| Text classification | SMS Spam Collection (5-fold cross-validation) | 36 | Feb 26, 2026 | ||
| Text classification | Yelp (5-fold cross-validation) | 36 | Feb 26, 2026 | ||
| Text classification | Drug Review Norgestimate (5-fold cross-validation) | 36 | Feb 26, 2026 |