CCLUE - Named Entity Recognition: leaderboard
CCLUE subtask measuring named entity recognition F1 on classical Chinese text.
Metric: F1 (%). Source: ethan-yt.github.io. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | guwenbert-base | 90.24 | |
| 2 | guwenbert-base-fs | 88.66 | |
| 3 | chinese-roberta-wwm-ext | 80.77 |
Interactive version: theaggregate.ai/benchmark?slug=cclue-named-entity-recognition · How It Works · Data refreshed daily, snapshot 2026-10-20.