Project AURIONAI Use-Cases Research & Innovation

C-Eval

52-discipline Chinese exam questions

Chinese languagesaturated
1scores
1models
0independent
0maintainer-run
1vendor-reported

Definition

Version
not in the notes
Category
Chinese language
Maintainer
SJTU, Tsinghua and Edinburgh authors, China
Status
saturated
Home page
https://cevalbenchmark.com/static/leaderboard.html

Sources

  1. C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models arxiv.org https://arxiv.org/abs/2305.08322
  2. cevalbenchmark.com/static/leaderboard.html https://cevalbenchmark.com/static/leaderboard.html

Scores

1 of 1 scores shown c-eval-scores.csv
ModelScoreWho ran itSettingView or populationDateSource
Alibaba (Qwen)Qwen1.5-72B84.1 %vendor-reported––4 Feb 2024qwenlm.github.io
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "C-Eval", https://aurion.semai.id/benchmarks/c-eval/, records of October 2026.