# CLUEbenchmark/SuperCLUE

SuperCLUE: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese

Repository: https://github.com/CLUEbenchmark/SuperCLUE
Canonical: https://ross.abutalabs.com/products/superclue
Homepage: https://www.superclueai.com
License Family: other
Topics: chatgpt, chinese, evaluation, foundation-models, gpt-4
Last push: 2026-02-06T11:40:46+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 66, release rhythm 35, longevity 87
- inputs: {"age_days": 1219, "days_push": 208, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3299, forks 110 (observed 2026-08-28T04:07:55.659935+00:00)

## What it is
SuperCLUE is a comprehensive benchmark for evaluating Chinese-language large language models across language understanding and generation, professional knowledge, agent capabilities, and safety. It publishes periodic leaderboards and annual reports ranking models like GPT-4, ERNIE, and Qwen.

## Use cases
- evaluate chinese llm performance
- compare chinese language models on a leaderboard
- benchmark foundation models for chinese tasks
- test llm agent tool-use and planning in chinese
- assess safety of chinese chatbots
- find the best chinese large language model

## When to choose
- you need standardized evaluation of Chinese-language LLMs
- you want to compare models on agent and safety capabilities
- you need published leaderboards and annual reports for reference

## When to avoid
- you need benchmarks for non-Chinese languages
- you need a runnable evaluation harness for your own private model weights without API access
- you need multilingual or English-only evaluation

## Facets
- artifact type: dataset
- maturity: active
- function: benchmarking, llm-inference, nlp
- domain: large-language-models, artificial-intelligence
- platform: python
- tags: llm-benchmark, chinese-language, model-evaluation, leaderboard, evaluation-suite, natural-language-processing, ai-agents

## Member repositories
- CLUEbenchmark/SuperCLUE (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:55.659935+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:22:40.740547+00:00, confidence not recorded.
  - readme: https://github.com/CLUEbenchmark/SuperCLUE (fetched 2026-08-28T04:07:55.659935+00:00, sha 35ed21ae90ed)
  - homepage: https://www.superclueai.com (fetched 2026-08-29T09:35:47.946662+00:00, sha d79a5b364489)
- Data as of 2026-08-30T08:39:29.467469+00:00.