# C-Eval

C-Eval is an AI benchmark; this page records what it measures and traces its data, grader, and scores to primary sources.

Evaluates Chinese foundation models with multiple-choice questions spanning 52 disciplines and four difficulty levels.

## Details

- Address: Online, Global
- Website: [cevalbenchmark.com/](<https://cevalbenchmark.com/>)
- Tags: Helpful, Science
- Category: Reasoning
- Status: Active
- Data licence: MIT
- Data access: open
- Grader: exact
- Organization: C-Eval authors
- Released: 2023-05
- Paper: [arxiv.org/abs/2305.08322](<https://arxiv.org/abs/2305.08322>)
- Leaderboard: [cevalbenchmark.com/](<https://cevalbenchmark.com/>)
- Repository: [github.com/hkust-nlp/ceval](<https://github.com/hkust-nlp/ceval>)
- Task count: 13,948
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is C-Eval?

C-Eval is at Online, Global.

### How do I contact C-Eval?

To contact C-Eval, visit https://cevalbenchmark.com/.

## Source

From [Benchmark primary sources](https://aibenchmarkindex.com/about), license CC0-1.0, checked 2026-10-15.

Last updated October 15, 2026.

## Links

- This benchmark on the [web page](<https://aibenchmarkindex.com/global/online/c-eval>)
- [Reasoning in Online](<https://aibenchmarkindex.com/global/online/category/reasoning.md>)
- [More benchmarks in Online](<https://aibenchmarkindex.com/global/online.md>)

> **Check before you compare.** Benchmark methods and leaderboards change. Follow the cited primary source before using a result in a decision.