AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
C-Eval
C-Eval is a comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundation models in a Chinese context. It comprises 13,948 multiple-choice questions across 52 diverse disciplines spanning humanities, science, and engineering, with four difficulty levels: middle school, high school, college, and professional. The benchmark includes C-Eval Hard, a subset of very challenging subjects requiring advanced reasoning abilities.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Not recorded
- Benchmark release
- Not recorded
- Collected
- 2026-08-17
- Modality
- text
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 18
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Qwen3.6 Plus | 0.933 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| Qwen3.5-397B-A17B | 0.93 | Not recorded | Not recorded | 2026-02-16 · model_announcement | LLM Stats |
| Kimi K2 Base | 0.925 | Not recorded | Not recorded | 2025-07-11 · model_announcement | LLM Stats |
| Qwen3.5-122B-A10B | 0.919 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| MiMo-V2.5-Pro | 0.915 | Not recorded | Not recorded | 2026-04-27 · model_announcement | LLM Stats |
| Qwen3.6-27B | 0.914 | Not recorded | Not recorded | 2026-04-21 · model_announcement | LLM Stats |
| Qwen3.5-27B | 0.905 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Qwen3.5-35B-A3B | 0.902 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Qwen3.6-35B-A3B | 0.9 | Not recorded | Not recorded | 2026-04-16 · model_announcement | LLM Stats |
| Kimi-k1.5 | 0.883 | Not recorded | Not recorded | 2025-01-20 · model_announcement | LLM Stats |
| Qwen3.5-9B | 0.882 | Not recorded | Not recorded | 2026-03-02 · model_announcement | LLM Stats |
| DeepSeek-V3 | 0.865 | Not recorded | Not recorded | 2024-12-25 · model_announcement | LLM Stats |
| Qwen3.5-4B | 0.851 | Not recorded | Not recorded | 2026-03-02 · model_announcement | LLM Stats |
| Qwen2 72B Instruct | 0.838 | Not recorded | Not recorded | 2024-07-23 · model_announcement | LLM Stats |
| Qwen2 7B Instruct | 0.772 | Not recorded | Not recorded | 2024-07-23 · model_announcement | LLM Stats |
| Qwen3.5-2B | 0.732 | Not recorded | Not recorded | 2026-03-02 · model_announcement | LLM Stats |
| Qwen3.5-0.8B | 0.505 | Not recorded | Not recorded | 2026-03-02 · model_announcement | LLM Stats |
| ERNIE 4.5 | 0.407 | Not recorded | Not recorded | 2025-06-25 · model_announcement | LLM Stats |