Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1239 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Language Modeling | WikiText and LAMBADA (test) | 24 | Apr 14, 2026 | ||
| Time-Series Anomaly Detection | MSL (test) | 24 | Feb 26, 2026 | ||
| Time-Series Anomaly Detection | PSM | 24 | Feb 26, 2026 | ||
| OOD detection | PubMed | 24 | May 14, 2026 | ||
| Mathematical Reasoning | OlympiadBench | 24 | Apr 14, 2026 | ||
| Time Series Forecasting | ECL | 24 | May 7, 2026 | ||
| Code Generation | LiveCodeBench (LCB) | 24 | May 21, 2026 | ||
| Goal-directed molecular optimization | PMO | 24 | May 7, 2026 | ||
| General Reasoning | General-R MMLU-stem, ARC-challenge (test) | 24 | Feb 26, 2026 | ||
| General Mathematics Reasoning | Math-G College-math, Math-OAI, Minerva-math (test) | 24 | Feb 26, 2026 | ||
| Competition Mathematics Reasoning | Math-C AIME24, AMC23, Olympiadbench (test) | 24 | Feb 26, 2026 | ||
| Document Question Answering | M3DocVQA | 24 | May 29, 2026 | ||
| Early Fake News Detection | GossipCop-P | 24 | Feb 26, 2026 | ||
| Early Fake News Detection | PolitiFact-P | 24 | Feb 26, 2026 | ||
| Recommendation | Electronic | 24 | Feb 26, 2026 | ||
| Recommendation | Health | 24 | Feb 26, 2026 | ||
| Recommendation | Kuaishou industrial-scale | 24 | Feb 26, 2026 | ||
| Sequential Recommendation | Toys (Overall) | 24 | Feb 26, 2026 | ||
| Sequential Recommendation | Douyin | 24 | Feb 26, 2026 | ||
| Sequential Recommendation | Amazon Toy | 24 | Apr 30, 2026 | ||
| Downstream retrieval | RAR-B | 24 | Feb 26, 2026 | ||
| Downstream retrieval | IMPLIRET | 24 | Feb 26, 2026 | ||
| Downstream retrieval | BRIGHT | 24 | Feb 26, 2026 | ||
| Generative Recommendation | Yelp (test) | 24 | Jun 2, 2026 | ||
| Software Task Completion | Word/Excel Tasks User Study 1.0 (test) | 24 | Feb 26, 2026 |