Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2062 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question Answering | CovidQA | 17 | Feb 26, 2026 | ||
| Question Answering | RAGTruth | 17 | Feb 26, 2026 | ||
| Speech-to-Speech Question-Answering | LlamaQ | 17 | Jul 8, 2026 | ||
| Academic Illustration Generation | PaperBananaBench | 17 | Jun 1, 2026 | ||
| Mathematical Reasoning | Olympiad bench | 17 | Feb 26, 2026 | ||
| Mathematical Reasoning | MATH500 | 17 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME24 | 17 | Feb 26, 2026 | ||
| General Performance | General Evaluation Suite | 17 | Feb 26, 2026 | ||
| Mathematical Reasoning | AMC | 17 | Feb 26, 2026 | ||
| Mathematical Reasoning | OlympiadBench | 17 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME25 | 17 | Feb 26, 2026 | ||
| Mathematical Reasoning | MATH500 | 17 | Feb 26, 2026 | ||
| Reward Modeling | IFBench | 17 | Feb 26, 2026 | ||
| Reward Modeling | InfoBench | 17 | Feb 26, 2026 | ||
| Reward Modeling | FollowBench | 17 | Feb 26, 2026 | ||
| Math Proof Verification | ProofBench | 17 | Apr 7, 2026 | ||
| Summarization | LongBench Summary (test) | 17 | Mar 20, 2026 | ||
| Question Answering | MSMARCO (test) | 17 | Feb 26, 2026 | ||
| Grounded ECG Interpretation | ECG-Grounding | 17 | Feb 26, 2026 | ||
| Online Language Modeling | PG-19 (Whole Book) | 17 | Feb 26, 2026 | ||
| GEC Metric Meta-evaluation | SEEDA-E Fluency Setting | 17 | Feb 26, 2026 | ||
| Scientific Reasoning | Aggregate GPQA, HLE, MMLU-Pro | 17 | Feb 26, 2026 | ||
| Scientific Reasoning | HLE | 17 | Feb 26, 2026 | ||
| Scientific Reasoning | GPQA General | 17 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME 24 | 17 | Feb 26, 2026 |