C-Eval

C-Eval is a benchmark for broad factual and academic knowledge. The official description says: "C-Eval - comprehensive Chinese evaluation benchmark across 52 subjects". Below we describe in simple words what benchmarks of this type generally examine.

C-Eval measures broad factual and academic knowledge. In detail, it checks:

• facts and concepts from many academic fields at once
• harder variants with several plausible answer options
• knowledge that goes beyond the model's training-set surface forms
• resisting the plausible-but-wrong answers deliberately included

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Official methodology note: C-Eval - comprehensive Chinese evaluation benchmark across 52 subjects.

What is the C-Eval benchmark?

C-Eval is a benchmark for broad factual and academic knowledge. The official description says: 'C-Eval - comprehensive Chinese evaluation benchmark across 52 subjects'. Below we describe in simple words what benchmarks of this type generally examine.

What does C-Eval test?

C-Eval mainly measures broad factual and academic knowledge. Concretely, it checks: facts and concepts from many academic fields at once; harder variants with several plausible answer options; knowledge that goes beyond the model's training-set surface forms.

How is the C-Eval score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get C-Eval data and scores?

The official source is https://cevalbenchmark.com/. The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/c-eval/scores) or pull it directly from the Open LLM Radar API with any HTTP client.