UniGenBench - Grammar: leaderboard
UniGenBench grammar slice measures generation under pronoun, consistency, and negation constraints.
Metric: Score. Source: huggingface.co. 63 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 91.21 | #343 |
Interactive version: theaggregate.ai/benchmark?slug=unigenbench-grammar · How It Works · Data refreshed daily, snapshot 2026-10-20.