Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 966 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | MATH 500 | 28 | Feb 26, 2026 | ||
| Output Ranking | ProductBench Home & Kitchen | 28 | Feb 26, 2026 | ||
| Promotion Success Rate | Tools & Home Improvement | 28 | Feb 26, 2026 | ||
| Promotion Success | Electronics | 28 | Feb 26, 2026 | ||
| Binary Lexical Semantic Change Detection | SemEval Subtask 1 (English) 2020 | 28 | Feb 26, 2026 | ||
| Document Understanding | AI2D | 28 | May 4, 2026 | ||
| STEM & Reasoning | MathVerse | 28 | Mar 12, 2026 | ||
| Long-context language modeling evaluation | HELMET | 28 | Feb 26, 2026 | ||
| Multilingual Language Understanding | MMLU-ProX | 28 | Jul 7, 2026 | ||
| Code Generation | MBPP | 28 | Feb 26, 2026 | ||
| Mathematical Reasoning | GSM8K | 28 | Feb 26, 2026 | ||
| Fluency | BOOKS | 28 | Feb 26, 2026 | ||
| Factuality | BIOS | 28 | Feb 26, 2026 | ||
| OCR-related understanding | DocVQA | 28 | May 29, 2026 | ||
| Question Answering | GPQA Natural Setting (test) | 28 | Feb 26, 2026 | ||
| Safety Evaluation | Safety Evaluation Suite HarmBench, StrongReject, WildJailbreak, XSTest | 28 | Feb 26, 2026 | ||
| Agentic task solving | AppWorld | 28 | Feb 26, 2026 | ||
| Code Generation | DS-1000 | 28 | Feb 26, 2026 | ||
| Multimodal Sentiment Analysis | CMU-MOSI cross-dataset evaluation (test) | 28 | Feb 26, 2026 | ||
| Reasoning | ARC-AGI 2 (test) | 28 | Apr 23, 2026 | ||
| Demand Forecasting | E-commerce Demand Country 04, Event-Driven Periods | 28 | Feb 26, 2026 | ||
| Demand Forecasting | E-commerce Demand Country 03, Event-Driven Periods | 28 | Feb 26, 2026 | ||
| Demand Forecasting | E-commerce Demand Country 02, Event-Driven Periods | 28 | Feb 26, 2026 | ||
| Demand Forecasting | E-commerce Center Overall 04 | 28 | Feb 26, 2026 | ||
| Demand Forecasting | E-commerce Center Overall 03 | 28 | Feb 26, 2026 |