Agentic Table Benchmark Reports
1 min read
Measured results for the Agentic Table agents. Each agent has its own section: a cover page with the results at a glance and the charts, and the full report below it.
Verbatim library answers
Returns the approved answer from the Answer Library verbatim, or refuses. Best result: Claude Opus 5.5 at low reasoning, right outcome on 97% of 325 questions (October–November 2026).
Composed answers from library sources
Composes an answer from eligible library sources and is designed to flag gaps. Claude Opus 5.5 and Gemini 4 Argon have the highest content score from an LLM judge (9.9 of 10) and, with Claude Opus 5, stay closest in tone; Gemini 4 Argon is much slower (October–November 2026).
Questionnaire question extraction
Turns an uploaded questionnaire document into the list of questions the table answers. On the 18 standard documents, the best models capture 91% of questions (GPT-6.1 Terra, GPT-5.6 Terra and GPT-6 Sol), and the differences between them are not significant; GPT-4o (no reasoning, production default) captures 31% (October–November 2026).