Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1921 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-input ciphertext multiplication | Multi-input ciphertext multiplication hardware_complexity L=K=24, N=2^16, w=64 | 18 | Feb 26, 2026 | ||
| 2D Localization | Indoor lab environment (5m x 5m) 5 locations v1 (test) | 18 | Feb 26, 2026 | ||
| Jailbreak Attack Evaluation | HarmBench (400 random samples) | 18 | Feb 26, 2026 | ||
| Mobile GUI Automation | PrivScreen | 18 | Feb 26, 2026 | ||
| Question Answering | HotpotQA (test) | 18 | Feb 26, 2026 | ||
| Natural Language Understanding | Zero-shot Downstream Benchmarks (BoolQ, ARC-E, ARC-C, HellaSwag) | 18 | Feb 26, 2026 | ||
| Web Research | Xbench DeepSearch | 18 | Feb 26, 2026 | ||
| Language Modeling | FineWeb-Edu 500M-token (val) | 18 | Feb 26, 2026 | ||
| LLM Inference | ToolBench | 18 | Feb 26, 2026 | ||
| LLM Inference | Merge | 18 | Feb 26, 2026 | ||
| Authorship segmentation | MAS (entire corpus) | 18 | Feb 26, 2026 | ||
| Attribution Faithfulness | AGNews | 18 | Feb 26, 2026 | ||
| Attribution Faithfulness | Sent140 | 18 | Feb 26, 2026 | ||
| Language Modeling and Question Answering | Short-context task suite (WikiText, LAMBADA, TriviaQA, PIQA, HellaSwag, WinoGrande, ARC-Easy, GPQA, Social IQA, OpenBookQA, SciQ) (test) | 18 | Feb 26, 2026 | ||
| Argumentative Fallacy Classification | Argumentative Fallacy Classification (AFC) | 18 | Feb 26, 2026 | ||
| Decision Correctness | HMDA (test) | 18 | Feb 26, 2026 | ||
| Process Verification | ProcessBench Without Standard Answers | 18 | Feb 26, 2026 | ||
| Process Verification | ProcessBench With Standard Answers | 18 | Feb 26, 2026 | ||
| Summarization | RAGTruth summarization (test) | 18 | Feb 26, 2026 | ||
| Zero-shot NLP Evaluation | Aggregate | 18 | Feb 26, 2026 | ||
| Commonsense Reasoning | COMM | 18 | Feb 26, 2026 | ||
| Language Modeling | NLP Standard Suite | 18 | Feb 26, 2026 | ||
| Scientific Reasoning | GPQA Diamond | 18 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME'25 | 18 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME'24 | 18 | Feb 26, 2026 |