RRepoGEO

REPOGEO REPORT · LITE

declare-lab/instruct-eval

Default branch main · commit 49bbd2ce · scanned 6/14/2026, 4:03:10 AM

GitHub: 553 stars · 45 forks

AI VISIBILITY SCORE
40 /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
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 declare-lab/instruct-eval, 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 project description in README

    Why:

    COPY-PASTE FIX
    Move the following text directly after the H1 and "Paper | Model | Leaderboard" links, before any other announcements: "InstructEval is a unified framework for quantitatively evaluating instruction-tuned large language models like Alpaca and Flan-T5 on held-out tasks. It seamlessly integrates both traditional automatic metrics (e.g., ROUGE, BLEU) and LLM-as-a-Judge based metrics, providing a holistic assessment of instruction-following capabilities."
  • mediumtopics#2
    Expand GitHub topics for better categorization

    Why:

    CURRENT
    instruct-tuning, llm
    COPY-PASTE FIX
    instruct-tuning, llm, llm-evaluation, llm-benchmark, evaluation-framework, nlp-evaluation, instruction-following
  • lowreadme#3
    Add a dedicated section highlighting InstructEval's unique differentiator

    Why:

    COPY-PASTE FIX
    Add a new section to the README, for example, "## Why Choose InstructEval?" or "## Our Approach", with text like: "InstructEval stands out by offering a unified framework for evaluating LLM instruction-following capabilities. It seamlessly integrates both traditional automatic metrics (e.g., ROUGE, BLEU) and advanced LLM-as-a-Judge based metrics, providing a comprehensive and holistic assessment of model performance."

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 declare-lab/instruct-eval
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
HELM
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. HELM · recommended 1×
  2. AlpacaEval · recommended 1×
  3. MT-Bench · recommended 1×
  4. Big Bench Hard · recommended 1×
  5. TruthfulQA · recommended 1×
  • CATEGORY QUERY
    How can I quantitatively assess the performance of instruction-following large language models?
    you: not recommended
    AI recommended (in order):
    1. HELM
    2. AlpacaEval
    3. MT-Bench
    4. Big Bench Hard
    5. TruthfulQA
    6. MMLU
    7. Amazon Mechanical Turk
    8. Scale AI
    9. Appen

    AI recommended 9 alternatives but never named declare-lab/instruct-eval. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking a framework to benchmark and compare various instruction-tuned LLMs on new tasks.
    you: not recommended
    AI recommended (in order):
    1. EleutherAI/lm-evaluation-harness (EleutherAI/lm-evaluation-harness)
    2. OpenAI Evals (openai/evals)
    3. Hugging Face Evaluate Library (huggingface/evaluate)
    4. DeepMind's Big-Bench Lite (BBL)
    5. LangChain Evaluation Module (langchain-ai/langchain)
    6. Ragas (explodinggradients/ragas)

    AI recommended 6 alternatives but never named declare-lab/instruct-eval. 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 declare-lab/instruct-eval?
    pass
    AI named declare-lab/instruct-eval explicitly

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

  • If a team adopts declare-lab/instruct-eval in production, what risks or prerequisites should they evaluate first?
    pass
    AI named declare-lab/instruct-eval 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 declare-lab/instruct-eval solve, and who is the primary audience?
    pass
    AI named declare-lab/instruct-eval 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 declare-lab/instruct-eval. 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/declare-lab/instruct-eval.svg)](https://repogeo.com/en/r/declare-lab/instruct-eval)
HTML
<a href="https://repogeo.com/en/r/declare-lab/instruct-eval"><img src="https://repogeo.com/badge/declare-lab/instruct-eval.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

declare-lab/instruct-eval — 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