REPOGEO REPORT · LITE

baichuan-inc/Baichuan-13B

Default branch main · commit 21017d59 · scanned 5/18/2026, 2:07:57 PM

GitHub: 2,931 stars · 233 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

33 /100

Critical

Category recall

0 / 2

Not recommended in any query

Rule findings

2 pass · 0 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 baichuan-inc/Baichuan-13B, 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 core value proposition to the top of the README

Why:

CURRENT

The README currently starts with a title, links, update information, and a table of contents, with the '介绍' (Introduction) section appearing further down.

COPY-PASTE FIX

Move the first paragraph of the '介绍' section (starting with 'Baichuan-13B 是由百川智能继 Baichuan-7B 之后开发的...') to immediately follow the initial title and links/badges, before the '更新信息' and '目录' sections.

mediumtopics#2

Add specific topics for commercial use and open-source LLMs

Why:

CURRENT

artificial-intelligence, benchmark, ceval, chatgpt, chinese, gpt-4, huggingface, large-language-models, mmlu, natural-language-processing

COPY-PASTE FIX

artificial-intelligence, benchmark, ceval, chatgpt, chinese, gpt-4, huggingface, large-language-models, mmlu, natural-language-processing, open-source-llm, commercial-use, llm-for-business

lowreadme#3

Emphasize competitive advantages more prominently in README

Why:

CURRENT

The comparison to LLaMA-13B is a sub-point within the '介绍' section, not immediately visible.

COPY-PASTE FIX

Add a concise bullet point or sentence near the top of the README (e.g., within the repositioned introduction or a new 'Highlights' section) explicitly stating: '训练数据量超过 LLaMA-13B 40%，是当前开源 13B 尺寸下训练数据量最多的模型。' (Trained on 1.4 trillion tokens, exceeding LLaMA-13B by 40%, making it the largest dataset for an open-source 13B model.)

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 baichuan-inc/Baichuan-13B

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

Llama 2 13B

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

Llama 2 13B · recommended 1×
Mistral 7B · recommended 1×
Vicuna-13B · recommended 1×
OpenOrca-Platypus2-13B · recommended 1×
Guanaco-13B · recommended 1×

CATEGORY QUERY
Which 13 billion parameter open-source language models are best for commercial use cases?
you: not recommended
AI recommended (in order):
1. Llama 2 13B
2. Mistral 7B
3. Vicuna-13B
4. OpenOrca-Platypus2-13B
5. Guanaco-13B
AI recommended 5 alternatives but never named baichuan-inc/Baichuan-13B. This is the gap to close.
Show full AI answer
CATEGORY QUERY
Seeking a robust large language model excelling in both Chinese and English natural language processing.
you: not recommended
AI recommended (in order):
1. GPT-4
2. Claude 3 Opus
3. ERNIE 4.0
4. Wenxin Qianfan
5. LLaMA 3
6. GLM-4
7. Yi-34B
AI recommended 7 alternatives but never named baichuan-inc/Baichuan-13B. This is the gap to close.
Show full AI answer

Objective checks

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

Metadata completeness
pass
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 baichuan-inc/Baichuan-13B?
pass
AI named baichuan-inc/Baichuan-13B explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts baichuan-inc/Baichuan-13B in production, what risks or prerequisites should they evaluate first?
pass
AI named baichuan-inc/Baichuan-13B 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 baichuan-inc/Baichuan-13B solve, and who is the primary audience?
pass
AI did not name baichuan-inc/Baichuan-13B — 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?

Embed your GEO score

Drop this badge into the README of baichuan-inc/Baichuan-13B. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

Live preview

MARKDOWN (README)

[![RepoGEO](https://repogeo.com/badge/baichuan-inc/Baichuan-13B.svg)](https://repogeo.com/en/r/baichuan-inc/Baichuan-13B)

HTML

<a href="https://repogeo.com/en/r/baichuan-inc/Baichuan-13B"><img src="https://repogeo.com/badge/baichuan-inc/Baichuan-13B.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

baichuan-inc/Baichuan-13B — 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