Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2772 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| General Utility Evaluation | Chatbot | 14 | Feb 26, 2026 | ||
| Structural Bias Evaluation | HANS | 14 | Feb 26, 2026 | ||
| Structural Bias Evaluation | MNLI | 14 | Feb 26, 2026 | ||
| Stereotypical Bias Mitigation | Unqover | 14 | Feb 26, 2026 | ||
| Big-Bench Hard Reasoning | BBH | 14 | Apr 7, 2026 | ||
| Long narrative understanding QA | Prelude | 14 | Feb 26, 2026 | ||
| Long narrative understanding QA | NarrativeQA | 14 | Feb 26, 2026 | ||
| Generative sense-making QA | Longbench | 14 | Feb 26, 2026 | ||
| Large Language Model Evaluation | 12-task evaluation suite composite (test) | 14 | Feb 26, 2026 | ||
| Hallucination Detection | HaluBench (test) | 14 | Feb 26, 2026 | ||
| Hallucination Detection | All detection benchmark sets average latest | 14 | Feb 26, 2026 | ||
| Word-level length-controlled question answering | ELI5 (test) | 14 | Feb 26, 2026 | ||
| Biography Generation | Biographies | 14 | Feb 26, 2026 | ||
| Summarization | GovReport | 14 | Feb 26, 2026 | ||
| Multi-hop Question Answering | HotpotQA | 14 | Feb 26, 2026 | ||
| Instruction Following | BabyAI | 14 | Feb 26, 2026 | ||
| Scientific Reasoning | SciWorld | 14 | Feb 26, 2026 | ||
| Membership Inference Attack | 14 | Mar 25, 2026 | |||
| Membership Inference Attack | CC News | 14 | Feb 26, 2026 | ||
| Membership Inference Attack | Amazon Reviews | 14 | Feb 26, 2026 | ||
| Membership Inference Attack | WikiText-103 | 14 | Feb 26, 2026 | ||
| General Language Understanding | CMMLU | 14 | Feb 26, 2026 | ||
| Explainability | Telugu | 14 | Feb 26, 2026 | ||
| Text Classification | Telugu | 14 | Feb 26, 2026 | ||
| Classification and Explainability | Hindi | 14 | Feb 26, 2026 |