GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026
49views this month
Decision brief
ACLUE is an evaluation benchmark for testing how well large language models understand ancient Chinese texts covering syntax, semantics, reasoning, and knowledge.
Good fit when
- When evaluating the performance of LLMs specifically on comprehending ancient Chinese language across 15 tasks
- If you are focusing on model assessment in domains such as syntax, semantics, reasoning, or specialized ancient Chinese knowledge
Avoid when
- For benchmarking modern Chinese or other languages not related to ancient Chinese comprehension
- When the focus is strictly on contemporary texts without a need for historical language understanding capabilities
Observed Jul 15, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (899d since push)
- As of Sep 6, 2026
- Provenance
- Not a fork · Personal account
- As of Sep 6, 2026
- Security (OSV)
- No lockfile
- As of Jul 11, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install ACLUESimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
ACLUE is an evaluation benchmark designed to assess the effectiveness of large language models (LLMs) on understanding ancient Chinese texts. The benchmark includes 15 tasks covering various domains such as syntax, semantics, reasoning, and knowledge.
Capability facts
- Languages
- python
Source: github.language · Sep 6, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Sep 6, 2026)
| [ChatGPT](https://openai.com/chatgpt) | **34.53** | **43.00** | 36Source link
Tags
README
<img src="fig/ACLUE.png" align="right" width="250" / ACLUE 古汉语语言理解评估基准 <h4 align="left" <p <b 简体中文</b <a href="README EN.md" English</a <p </h4 <p align="left" style="display: flex; flex direction: row; justify content: center; align items: center" 📄 <a href="https://arxiv.org/a...
For agents
This page has a .md twin and JSON over the API.