# C-Eval leaderboard

Knowledge benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/knowledge-c-eval

Every model the catalog carries a published C-Eval value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Knowledge |
| Measure | Multiple choice questions |
| Tasks | Chinese academic and professional exams |
| Difficulty | High school to professional level |
| Published by | [C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models](https://arxiv.org/abs/2305.08322) |

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

## C-Eval ranking

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 | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Kimi K2.5](https://modelchoice.dev/models/kimi-k2-5) | Moonshot AI | 94 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Qwen3.6 Plus](https://modelchoice.dev/models/qwen3-6-plus) | Alibaba | 93.3 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Qwen3.5 397B](https://modelchoice.dev/models/qwen3-5-397b) | Alibaba | 93 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Claude Opus 4.5](https://modelchoice.dev/models/claude-opus-4-5) | Anthropic | 92.2 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Qwen3.6-27B](https://modelchoice.dev/models/qwen3-6-27b) | Alibaba | 91.4 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Qwen3.6-35B-A3B](https://modelchoice.dev/models/qwen3-6-35b-a3b) | Alibaba | 90 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Qwen3 235B-A22B (Reasoning)](https://modelchoice.dev/models/qwen3-235b-a22b-reasoning) | Alibaba | 89.6 | Observed 2026-11-21 · source benchlm:models |
| 8 | [QwQ-32B](https://modelchoice.dev/models/qwq-32b) | Alibaba | 88.4 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Qwen3 32B (Reasoning)](https://modelchoice.dev/models/qwen3-32b-reasoning) | Alibaba | 87.3 | Observed 2026-11-21 · source benchlm:models |
| 10 | [Qwen3 235B-A22B](https://modelchoice.dev/models/qwen3-235b-a22b) | Alibaba | 86.1 | Observed 2026-11-21 · source benchlm:models |
| 11 | [LongCat-Flash-Lite-Sparse](https://modelchoice.dev/models/longcat-flash-lite-sparse) | Meituan | 85.76 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Qwen3 32B](https://modelchoice.dev/models/qwen3-32b) | Alibaba | 83.3 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
