RRepoGEO

REPOGEO REPORT · LITE

IDEA-CCNL/Fengshenbang-LM

Default branch main · commit c8fb7b84 · scanned 6/27/2026, 5:32:40 PM

GitHub: 4,128 stars · 375 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE
28 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 1 warn · 0 fail
Objective metadata checks
AI knows your name
2 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface IDEA-CCNL/Fengshenbang-LM, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Reposition README's opening to clarify project identity

    Why:

    CURRENT
    The README starts with navigation links and then '# 封神榜科技成果'.
    COPY-PASTE FIX
    Insert the following paragraph immediately after the navigation links and before '# 封神榜科技成果':

"Fengshenbang-LM (封神榜大模型) is a comprehensive open-source system for large language models, developed by IDEA Research Institute's Cognitive Computing and Natural Language Research Center. It provides foundational infrastructure for Chinese AIGC and cognitive intelligence, offering a suite of pre-trained models, tools, and resources for researchers and developers."
  • mediumhomepage#2
    Add homepage URL to repository metadata

    Why:

    COPY-PASTE FIX
    https://fengshenbang-lm.com
  • lowreadme#3
    Explicitly state target audience and use cases in README

    Why:

    CURRENT
    The README primarily focuses on achievements and events.
    COPY-PASTE FIX
    Add a dedicated section (e.g., '## 目标用户与应用场景 (Target Users & Use Cases)') in the README, detailing who benefits from Fengshenbang-LM (e.g., AI researchers, developers, enterprises building Chinese AIGC applications) and what problems it helps them solve.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface IDEA-CCNL/Fengshenbang-LM
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Hugging Face Transformers
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. Hugging Face Transformers · recommended 2×
  2. PaddleNLP · recommended 1×
  3. OpenBMB · recommended 1×
  4. MindSpore · recommended 1×
  5. Megatron-LM · recommended 1×
  • CATEGORY QUERY
    What open-source large language model frameworks are best for Chinese AIGC development?
    you: not recommended
    AI recommended (in order):
    1. Hugging Face Transformers
    2. PaddleNLP
    3. OpenBMB
    4. MindSpore
    5. Megatron-LM

    AI recommended 5 alternatives but never named IDEA-CCNL/Fengshenbang-LM. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking a robust platform offering various pre-trained multimodal models for Chinese natural language processing.
    you: not recommended
    AI recommended (in order):
    1. Baidu ERNIE
    2. Tencent Hunyuan
    3. Alibaba M6
    4. Huawei Pangu-Σ
    5. SenseTime SenseChat/SenseMirage
    6. OpenAI CLIP
    7. Hugging Face Transformers

    AI recommended 7 alternatives but never named IDEA-CCNL/Fengshenbang-LM. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    warn

    Suggestion:

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of IDEA-CCNL/Fengshenbang-LM?
    pass
    AI did not name IDEA-CCNL/Fengshenbang-LM — likely talking about a different project

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts IDEA-CCNL/Fengshenbang-LM in production, what risks or prerequisites should they evaluate first?
    pass
    AI named IDEA-CCNL/Fengshenbang-LM explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo IDEA-CCNL/Fengshenbang-LM solve, and who is the primary audience?
    pass
    AI named IDEA-CCNL/Fengshenbang-LM explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of IDEA-CCNL/Fengshenbang-LM. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/IDEA-CCNL/Fengshenbang-LM.svg)](https://repogeo.com/en/r/IDEA-CCNL/Fengshenbang-LM)
HTML
<a href="https://repogeo.com/en/r/IDEA-CCNL/Fengshenbang-LM"><img src="https://repogeo.com/badge/IDEA-CCNL/Fengshenbang-LM.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

IDEA-CCNL/Fengshenbang-LM — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite