reasoning benchmark
C-Eval Leaderboard
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.
Updated Aug 17, 2026
Models18
Model coverage18
MetricScore
EvidenceB
C-Eval Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score93.3% | Percentile100.0% | Participants18 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score93.0% | Percentile94.1% | Participants18 | EvidenceC | Evaluated |
| Rank03 | ModelMA | Score92.5% | Percentile88.2% | Participants18 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score91.9% | Percentile82.3% | Participants18 | EvidenceC | Evaluated |
| Rank05 | ModelXI | Score91.5% | Percentile76.5% | Participants18 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score91.4% | Percentile70.6% | Participants18 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score90.5% | Percentile64.7% | Participants18 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score90.2% | Percentile58.8% | Participants18 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score90.0% | Percentile52.9% | Participants18 | EvidenceC | Evaluated |
| Rank10 | ModelMA | Score88.3% | Percentile47.1% | Participants18 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score88.2% | Percentile41.2% | Participants18 | EvidenceC | Evaluated |
| Rank12 | ModelDE | Score86.5% | Percentile35.3% | Participants18 | EvidenceC | Evaluated |
| Rank13 | ModelAC | Score85.1% | Percentile29.4% | Participants18 | EvidenceC | Evaluated |
| Rank14 | ModelAC | Score83.8% | Percentile23.5% | Participants18 | EvidenceC | Evaluated |
| Rank15 | ModelAC | Score77.2% | Percentile17.6% | Participants18 | EvidenceC | Evaluated |
| Rank16 | ModelAC | Score73.2% | Percentile11.8% | Participants18 | EvidenceC | Evaluated |
| Rank17 | ModelAC | Score50.5% | Percentile5.9% | Participants18 | EvidenceC | Evaluated |
| Rank18 | ModelBA | Score40.7% | Percentile0.0% | Participants18 | EvidenceC | Evaluated |
C-Eval Highlights
The leading models and scores on this benchmark.
C-Eval Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for C-Eval
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis c-eval AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01ACQwen3.6 PlusAlibaba Cloud / Qwen Team
- Score
- 93.3%
- Price
- $0.50 input / $3.0 output per 1M tokens
- Speed
- Up to 16 tok/s via Together
Strengths
- Ranks #1 of 18 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures C-Eval, not total model capability
- 02ACQwen3.5-397B-A17BAlibaba Cloud / Qwen Team
- Score
- 93.0%
- Price
- $0.60 input / $3.6 output per 1M tokens
Strengths
- Ranks #2 of 18 compared models
- 94th percentile on this benchmark
- C evidence result
Considerations
- This result measures C-Eval, not total model capability
- 03MAKimi K2 BaseMoonshot AI
- Score
- 92.5%
- Price
- $0.60 input / $2.5 output per 1M tokens
- Speed
- Up to 45 tok/s via Novita
Strengths
- Ranks #3 of 18 compared models
- 88th percentile on this benchmark
- C evidence result
Considerations
- This result measures C-Eval, not total model capability
- 04ACQwen3.5-122B-A10BAlibaba Cloud / Qwen Team
- Score
- 91.9%
- Price
- $0.40 input / $3.2 output per 1M tokens
Strengths
- Ranks #4 of 18 compared models
- 82th percentile on this benchmark
- C evidence result
Considerations
- This result measures C-Eval, not total model capability
- 05XIMiMo-V2.5-ProXiaomi
- Score
- 91.5%
- Price
- $0.43 input / $0.87 output per 1M tokens
- Speed
- Up to 69 tok/s via Novita
Strengths
- Ranks #5 of 18 compared models
- 76th percentile on this benchmark
- C evidence result
Considerations
- This result measures C-Eval, not total model capability
Selection summary
Best AI Models for C-Eval
Qwen3.6 Plus currently leads C-Eval with 93.3%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is C-Eval?
What C-Eval measures and how its scores work.
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.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- C-Eval
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- c-eval|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about C-Eval.
Which model scores highest on C-Eval?
Qwen3.6 Plus is currently ranked first with 93.3%.
What does C-Eval measure?
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.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
18 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.