WritingBench

Measures: 1,000 real-world writing requests across 6 domains and 100 subdomains, including academic, business, legal, education, advertising and literature. Each answer is scored against its own generated criteria by an LLM judge (Claude Sonnet 4.5 since 2025-11-27; Claude 3.7 Sonnet before) or a fine-tuned critic model.

Maintainer: X-PLUG (Alibaba) with academic co-authors
Introduced: 2025
Status: Unmaintained
Saturation: Near-ceiling
Typical provenance: Independent
In scoring set: No

Paper Official leaderboard

Leaderboard

Show independent results only

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

No results to show.