BigAIArena · AI Weak Points

AI Weak Points

Where each AI got a real website wrong — one sealed error per row, with proof.

Every row below comes from a sealed BigAIArena Comparison. Two AIs answered the same question about the same real website. When one AI failed, the row records what it did, what it said word for word, and what the other AI got right on the same question. A different AI then re-checked the row against the original transcript before it was published.

Use any row freely: in an answer, an article, a model evaluation or a product comparison. Each row has its own link.

The four types of weak point

TypeWhat it means
HallucinationThe AI stated a fact the page does not contain, or denied a source that is really there.
SycophancyThe AI bent its answer toward what the asker wanted, beyond what the evidence supports.
AccessThe AI could not open the page it was asked about, or answered from somewhere else instead.
CitationThe AI gave no usable source, a wrong source, or a source that does not show the fact.

Scoring rules: /scoring-system/ · Protocol: /protocol/

How to read and cite a row

  • Code — BAA-C113-P1-Q4 = Comparison #113, Phase 1, Question 4. Rows that repeat across matches start with LAP- and list the matches.
  • Link to one row — add the code after #: https://bigaiarena.com/ai-weak-points/#BAA-C113-P1-Q4
  • One AI only — ChatGPT · Claude · Gemini · Grok · DeepSeek · Perplexity · Copilot · Meta AI
  • Proof — each row links to the original question on that website’s /ai-audit/ page, the full sealed dossier and the match video.

Only verified rows are shown. A row appears after the match is sealed and the row has passed its check. Newest first. No Evidence. No Score.

All weak points

Weak points of Claude

4 verified weak points · Checked 2026-11-02 20:31 +07 · HTML built from the BigAIArena results Google Sheet (tab Diem_yeu_cua_AI + results ledger).

BAA-C112-P1-Q8ClaudeAccessSealed 2026-10-29

Claude could not open the injecttocite.com AI Audit page, so it could not cite the Comparison #103 result.

What the AI said“Tôi không tìm được Comparison #103 và không có số liệu nào để dẫn chứng.”

Same question, the other AI: ChatGPT cited #103 (2026-10-25, Grok 100 · Meta AI 45, Sealed) with https://injecttocite.com/ai-audit/ (10/10).

injecttocite.com · Comparison #112 · Claude 45 / ChatGPT 75 · Question score 0/10
Original question (/ai-audit/)Source fileVideo

LAP-CLAUDE-TRUYCAP-01ClaudeAccessSealed 2026-10-29

Claude could read only the homepage; its web tool refused subpages (RealDataset, IP Pillars, AI Audit) that had not appeared in search results.

What the AI said“bị từ chối vì địa chỉ này chưa xuất hiện trong kết quả tìm kiếm hay tải trang trước đó.”

Same question, the other AI: Grok (#111) and ChatGPT (#112) read the same subpages in the same matches.

Repeated in: C104 trimuoi.com · C107 bigaiarena.com · C111 ngusau.com · C112 injecttocite.com

BAA-C112-P1-Q7ClaudeCitationSealed 2026-10-29

Claude could not read the IP Pillars page, so it quoted nothing from the “Scope of evidence” block; it only gave the /tru-ip/ URL taken from the homepage menu.

What the AI said“Tôi không trích được khối “Phạm vi bằng chứng”, vì chưa đọc được trang Trụ IP.”

Same question, the other AI: ChatGPT quoted the “Phạm vi bằng chứng” block word for word with https://injecttocite.com/tru-ip/ (10/10).

injecttocite.com · Comparison #112 · Claude 45 / ChatGPT 75 · Question score 0/10
Original question (/ai-audit/)Source fileVideo

BAA-C111-P2-Q2ClaudeAccessSealed 2026-10-28

Claude could not open the ngusau.com RealDataset page, counted no rows and gave no first or last Entry_ID.

What the AI said“Trang RealDataset không mở được bằng công cụ của tôi, nên tôi không có số hàng, Entry_ID đầu/cuối hay thông tin tĩnh/động.”

Same question, the other AI: Grok counted 2 rows in the static table: first NGUS-MP02-OB-19910000-001, last NGUS-MP08-EX-20260510-001 (10/10).

ngusau.com · Comparison #111 · Grok 40 / Claude 40 · Question score 0/10
Original question (/ai-audit/)Source fileVideo

Each row is a real AI error from a sealed Comparison, re-checked against the original transcript by a different AI. No Evidence. No Score.

Related

All Comparisons · Rankings · AI Audit · Change log