Open-rewrite
OpenRewriteEval is a benchmark for evaluating open-ended rewriting of long-form texts, covering a wide variety of rewriting types expressed through natural language instructions including formality, expansion, conciseness, paraphrasing, and tone and style transfer.
Llama 3.2 3B Instruct from Meta currently leads the Open-rewrite leaderboard with a score of 0.401 across 1 evaluated AI models.
What Open-rewrite measures
Open-rewrite is a text benchmark that evaluates large language models on language and writing tasks. LLM Stats tracks 1 model on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.4, with the leader reaching 0.4.
Compare leaders on the best AI for language and best AI for writing leaderboards.
Publication
- Paper
- RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting
- Authors
- Lei Shu, Liangchen Luo, Jayakumar Hoskere, Yun Zhu, and 4 others
- Published
- arXiv
- 2305.15685
Abstract
Large Language Models (LLMs) have demonstrated impressive capabilities in creative tasks such as storytelling and E-mail generation. However, as LLMs are primarily trained on final text results rather than intermediate revisions, it might be challenging for them to perform text rewriting tasks. Most studies in the rewriting tasks focus on a particular transformation type within the boundaries of single sentences. In this work, we develop new strategies for instruction tuning and reinforcement learning to better align LLMs for cross-sentence rewriting tasks using diverse wording and structures expressed through natural languages including 1) generating rewriting instruction data from Wiki edits and public corpus through instruction generation and chain-of-thought prompting; 2) collecting comparison data for reward model training through a new ranking function. To facilitate this research, we introduce OpenRewriteEval, a novel benchmark covers a wide variety of rewriting types expressed through natural language instructions. Our results show significant improvements over a variety of baselines. The public repository is available on GitHub under Google Research (https://github.com/google-research/google-research/tree/master/rewritelm).
Llama 3.2 3B Instruct leads with 40.1%.
Progress Over Time
Interactive timeline showing model performance evolution on Open-rewrite
Open-rewrite Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | 3B | — | — |
FAQ
Common questions about Open-rewrite.
More evaluations to explore
Related benchmarks in the same category
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
Multilingual Massive Multitask Language Understanding dataset released by OpenAI, featuring professionally translated MMLU test questions across 14 languages including Arabic, Bengali, German, Spanish, French, Hindi, Indonesian, Italian, Japanese, Korean, Portuguese, Swahili, Yoruba, and Chinese. Contains approximately 15,908 multiple-choice questions per language covering 57 subjects.
An improved version of the MMLU benchmark featuring manually re-annotated questions to identify and correct errors in the original dataset. Provides more reliable evaluation metrics for language models by addressing dataset quality issues found in the original MMLU.
Extended version of MMLU-Pro providing additional challenging multiple-choice questions for evaluating language models across diverse academic and professional domains. Built on the foundation of the Massive Multitask Language Understanding benchmark framework.
Arena-Hard-Auto is an automatic evaluation benchmark for instruction-tuned LLMs consisting of 500 challenging real-world prompts curated by BenchBuilder. It includes open-ended software engineering problems, mathematical questions, and creative writing tasks. The benchmark uses LLM-as-a-Judge methodology with GPT-4.1 and Gemini-2.5 as automatic judges to approximate human preference. Arena-Hard achieves 98.6% correlation with human preference rankings and provides 3x higher separation of model performances compared to MT-Bench, making it highly effective for distinguishing between models of similar quality.