C-Eval leaderboard
As of November 14, 2026, among the results listed here, Kimi-K2-Base has the highest reported C-Eval score, 92.5 (Base model evaluation results; EM), published by Moonshot AI. 1 model has a C-Eval result in our records.
Scores as the model makers published them, not re-run by us; each row links to its announcement.
Best reported score
92.5
Reported by Moonshot AI, July 11, 2025 · Base model evaluation results; EM
1 model ranked · 1 maker
| Rank | Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|---|
| 1 | Kimi-K2-Base | 92.5 | Base model evaluation results; EM | Moonshot AI | July 11, 2025 (model release) |
How much to trust these numbers
- Source
- Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
- Settings
- All ranked results use the same reported setting.
- Freshness
- Published July 11, 2025.
What C-Eval measures
C-Eval asks models to answer Chinese multiple-choice questions across 52 disciplines and four difficulty levels; its accuracy score is the percentage answered correctly. Source: C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models