Skip to content

C-Eval

A Chinese-language academic and professional benchmark spanning humanities, social science, STEM, and applied subjects.

10 models

Higher is better.

  1. 1Kimi K2.5Moonshot AI94.0
  2. 2Qwen3.6 PlusAlibaba93.3
  3. 3Qwen3.5 397BAlibaba93.0
  4. 4Claude Opus 4.5Anthropic92.2
  5. 5Qwen3.6-27BAlibaba91.4
  6. 6Qwen3.6-35B-A3BAlibaba90.0
  7. 7QwQ-32BAlibaba88.4
  8. 8Qwen3 235B-A22BAlibaba86.1
  9. 9LongCat-Flash-Lite-SparseMeituan85.8
  10. 10Qwen3 32BAlibaba83.3
Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric
Multiple choice questions
Tasks
Chinese academic and professional exams
Authors
C-Eval authors (2023)

Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.