Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Knowledge benchmark
Every model the catalog carries a published C-Eval value for, ranked by that value.
A Chinese-language academic and professional benchmark spanning humanities, social science, STEM, and applied subjects. 12 models in the ModelScale catalog have a published value.
Each point is a model with a published C-Eval value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
12 models with a published C-Eval value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Multiple choice questions |
|---|---|---|---|
| 1 | Moonshot AI | 94 | |
| 2 | Alibaba | 93.3 | |
| 3 | Alibaba | 93 | |
What the benchmark measures and how its value is published, from the source’s own record.
C-Eval is a knowledge benchmark published by C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models. A Chinese-language academic and professional benchmark spanning humanities, social science, STEM, and applied subjects. Its evaluation set is described by the source as chinese academic and professional exams. The source rates its difficulty as high school to professional level.
Each model's result is published by C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models as multiple choice questions. ModelScale prints that value exactly as published, and never converts or rescales it. This page ranks the 12 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
| 4 |
| Anthropic |
| 92.2 |
| 5 | Alibaba | 91.4 |
| 6 | Alibaba | 90 |
| 7 | Alibaba | 89.6 |
| 8 | Alibaba | 88.4 |
| 9 | Alibaba | 87.3 |
| 10 | Alibaba | 86.1 |
| 11 | Meituan | 85.76 |
| 12 | Alibaba | 83.3 |
Evidence key: Observed
Rows are ordered by the value C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.