RRepoGEO

REPOGEO REPORT · LITE

rdi-berkeley/agents-last-exam

Default branch main · commit 122fa43b · scanned 6/17/2026, 7:22:40 AM

GitHub: 686 stars · 26 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 rdi-berkeley/agents-last-exam, 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 purpose and counter misinterpretation

    Why:

    CURRENT
    Agents' Last Exam aims to build the broadest-coverage agent evaluation benchmark to date...
    COPY-PASTE FIX
    Agents' Last Exam is the leading open evaluation framework and benchmark for AI agents, *not* a course-specific assessment. It aims to build the broadest-coverage agent evaluation benchmark to date...
  • hightopics#2
    Add specific topics to improve AI categorization

    Why:

    COPY-PASTE FIX
    ai-agents, agent-evaluation, ai-benchmark, llm-agents, evaluation-framework, real-world-tasks, long-horizon-tasks, economic-value
  • mediumabout#3
    Update repository description for clarity and better categorization

    Why:

    CURRENT
    Agents' Last Exam
    COPY-PASTE FIX
    An open evaluation framework and benchmark to challenge and measure AI agents on economically valuable, real-world tasks.

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 rdi-berkeley/agents-last-exam
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
MLflow
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. MLflow · recommended 2×
  2. OpenAI Evals · recommended 2×
  3. Scale AI · recommended 1×
  4. Appen · recommended 1×
  5. Surge AI · recommended 1×
  • CATEGORY QUERY
    How can I effectively evaluate and benchmark AI agent performance on complex, real-world tasks?
    you: not recommended
    AI recommended (in order):
    1. Scale AI
    2. Appen
    3. Surge AI
    4. MLflow
    5. LangChain
    6. LlamaIndex
    7. LangSmith
    8. OpenAI Evals
    9. Weights & Biases
    10. Galileo

    AI recommended 10 alternatives but never named rdi-berkeley/agents-last-exam. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What framework helps measure AI agent capabilities across diverse industries with verifiable outcomes?
    you: not recommended
    AI recommended (in order):
    1. MLflow
    2. Weights & Biases (W&B)
    3. Arize AI
    4. Fiddler AI
    5. OpenAI Evals
    6. scikit-learn
    7. pandas
    8. numpy
    9. matplotlib
    10. seaborn

    AI recommended 10 alternatives but never named rdi-berkeley/agents-last-exam. 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 rdi-berkeley/agents-last-exam?
    pass
    AI named rdi-berkeley/agents-last-exam explicitly

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

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

Subscribe to Pro for deep diagnoses

rdi-berkeley/agents-last-exam — 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