REPOGEO REPORT · LITE

BAAI-DCAI/Bunny

Default branch main · commit 08273acb · scanned 5/11/2026, 5:32:39 PM

GitHub: 1,053 stars · 76 forks

AI VISIBILITY SCORE

35 /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

3 / 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 BAAI-DCAI/Bunny, 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

highabout#1

Update the About section description to highlight key differentiators

Why:

CURRENT

A family of lightweight multimodal models.

COPY-PASTE FIX

A family of lightweight and efficient multimodal models (MLLMs) supporting high-resolution images and multiple language backbones like Llama-3 and Qwen1.5.

mediumreadme#2

Enhance the README's opening paragraph to emphasize unique features

Why:

CURRENT

Bunny is a family of lightweight but powerful multimodal models. It offers multiple plug-and-play vision encoders, like **EVA-CLIP, SigLIP** and language backbones, including **Llama-3-8B, Phi-3-mini, Phi-1.5, StableLM-2, Qwen1.5, MiniCPM and Phi-2**. To compensate for the decrease in model size, we construct more informative training data by curated selection from a broader data source.

COPY-PASTE FIX

Bunny is a family of lightweight yet powerful multimodal models (MLLMs) designed for efficient vision and language understanding. It offers multiple plug-and-play vision encoders (e.g., EVA-CLIP, SigLIP) and language backbones (e.g., Llama-3-8B, Phi-3-mini, Qwen1.5), notably featuring Bunny-Llama-3-8B-V as a pioneering VLM that accepts high-resolution images up to 1152x1152. To compensate for the decrease in model size, we construct more informative training data by curated selection from a broader data source.

lowhomepage#3
Add a homepage URL to the repository's About section
Why:
COPY-PASTE FIX
```
https://github.com/BAAI-DCAI/Bunny
```

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 BAAI-DCAI/Bunny

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

LLaVA

Recommended in 2 of 2 queries

COMPETITOR LEADERBOARD

LLaVA · recommended 2×
MiniGPT-4 · recommended 1×
BLIP-2 · recommended 1×
OpenFlamingo · recommended 1×
CoCa · recommended 1×

CATEGORY QUERY
What are some lightweight multimodal models for efficient vision and language understanding?
you: not recommended
AI recommended (in order):
1. MiniGPT-4
2. LLaVA
3. BLIP-2
4. OpenFlamingo
5. CoCa
AI recommended 5 alternatives but never named BAAI-DCAI/Bunny. This is the gap to close.
Show full AI answer
CATEGORY QUERY
I need a multimodal model supporting high-resolution images and multiple languages like Chinese.
you: not recommended
AI recommended (in order):
1. GPT-4o
2. Gemini 1.5 Pro
3. Claude 3 Opus / Sonnet
4. LLaVA
5. CogVLM
AI recommended 5 alternatives but never named BAAI-DCAI/Bunny. 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 BAAI-DCAI/Bunny?
pass
AI named BAAI-DCAI/Bunny explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts BAAI-DCAI/Bunny in production, what risks or prerequisites should they evaluate first?
pass
AI named BAAI-DCAI/Bunny 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 BAAI-DCAI/Bunny solve, and who is the primary audience?
pass
AI named BAAI-DCAI/Bunny 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 BAAI-DCAI/Bunny. 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/BAAI-DCAI/Bunny.svg)](https://repogeo.com/en/r/BAAI-DCAI/Bunny)

HTML

<a href="https://repogeo.com/en/r/BAAI-DCAI/Bunny"><img src="https://repogeo.com/badge/BAAI-DCAI/Bunny.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

BAAI-DCAI/Bunny — 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