REPOGEO REPORT · LITE

poetiq-ai/poetiq-arc-agi-solver

Default branch main · commit a6947cff · scanned 5/15/2026, 10:38:21 PM

GitHub: 1,273 stars · 214 forks

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 poetiq-ai/poetiq-arc-agi-solver, 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

hightopics#1

Add specific topics for ARC-AGI and AI benchmarks

Why:

COPY-PASTE FIX

arc-agi, agi-solver, abstract-reasoning, ai-benchmark, state-of-the-art, llm-reasoning, reproduction-framework

highreadme#2

Reposition README opening to emphasize 'reproduction framework'

Why:

CURRENT

# Poetiq: SOTA Reasoning on ARC-AGI

[](https://opensource.org/licenses/MIT)
[](https://www.python.org/downloads/)
[](https://arcprize.org/)

This repository allows reproduction of **Poetiq's** record-breaking submission to the ARC-AGI-1 and ARC-AGI-2 benchmarks.

COPY-PASTE FIX

# Poetiq ARC-AGI Solver: Reproduce SOTA Abstract Reasoning Results

[](https://opensource.org/licenses/MIT)
[](https://www.python.org/downloads/)
[](https://arcprize.org/)

This repository provides the official framework to reproduce Poetiq's record-breaking, state-of-the-art submissions to the ARC-AGI-1 and ARC-AGI-2 benchmarks.

mediumabout#3

Clarify the repository description to highlight its function as a solver framework

Why:

CURRENT

This repository allows reproduction of Poetiq's record-breaking submission to the ARC-AGI-1 and ARC-AGI-2 benchmarks.

COPY-PASTE FIX

This repository provides the official solver framework to reproduce Poetiq's record-breaking, state-of-the-art submissions to the ARC-AGI-1 and ARC-AGI-2 benchmarks.

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 poetiq-ai/poetiq-arc-agi-solver

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

Perceiver IO / Perceiver

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

Perceiver IO / Perceiver · recommended 1×
PyTorch Geometric · recommended 1×
DeepMind's Graph Nets library · recommended 1×
Vision Transformers (ViT) · recommended 1×
DeepMind's AlphaGeometry · recommended 1×

CATEGORY QUERY
How can I reproduce state-of-the-art results for abstract reasoning challenges using AI models?
you: not recommended
AI recommended (in order):
1. Perceiver IO / Perceiver
2. PyTorch Geometric
3. DeepMind's Graph Nets library
4. Vision Transformers (ViT)
5. DeepMind's AlphaGeometry
6. DreamCoder
7. AlphaZero
AI recommended 7 alternatives but never named poetiq-ai/poetiq-arc-agi-solver. This is the gap to close.
Show full AI answer
CATEGORY QUERY
What tools help evaluate and improve AI performance on general intelligence benchmarks?
you: not recommended
AI recommended (in order):
1. EleutherAI's LM Evaluation Harness
2. OpenAI Evals
3. BigBench
4. Hugging Face `evaluate` library
5. HumanEval
6. MMLU
7. LangChain
8. LlamaIndex
AI recommended 8 alternatives but never named poetiq-ai/poetiq-arc-agi-solver. 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 poetiq-ai/poetiq-arc-agi-solver?
pass
AI named poetiq-ai/poetiq-arc-agi-solver explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts poetiq-ai/poetiq-arc-agi-solver in production, what risks or prerequisites should they evaluate first?
pass
AI named poetiq-ai/poetiq-arc-agi-solver 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 poetiq-ai/poetiq-arc-agi-solver solve, and who is the primary audience?
pass
AI did not name poetiq-ai/poetiq-arc-agi-solver — 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 poetiq-ai/poetiq-arc-agi-solver. 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/poetiq-ai/poetiq-arc-agi-solver.svg)](https://repogeo.com/en/r/poetiq-ai/poetiq-arc-agi-solver)

HTML

<a href="https://repogeo.com/en/r/poetiq-ai/poetiq-arc-agi-solver"><img src="https://repogeo.com/badge/poetiq-ai/poetiq-arc-agi-solver.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

poetiq-ai/poetiq-arc-agi-solver — 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