PulseAugur
EN
LIVE 09:29:00

Claude Opus-5 lags behind frontier models in Wikipedia abstract communication game · arXiv research

By PulseAugur Editorial · [1 sources] ·

A new research paper published on arXiv evaluates six frontier language models on a communication efficiency task called the log(N)-Questions game. The game involves two instances of the same model, one acting as a questioner and the other as an answerer, to identify a target document from a set of N Wikipedia abstracts using only log(N) yes/no questions. Claude Opus-5 performed significantly worse than GLM 5.3, GPT 5.6 "Sol", Grok 4.6, Gemini 3.8 Flash, and Kimi K3, with win rates declining as the document set size increased. The study found that information per question correlates with win rate, and models that partition documents by title performed better. AI

IMPACT Highlights differences in communication efficiency and strategic document partitioning among leading LLMs, potentially influencing future model development.

RANK_REASON Research paper evaluating frontier language models on a novel task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Claude Opus-5 lags behind frontier models in Wikipedia abstract communication game · arXiv research

How we ranked this

Signal score
13 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Research paper evaluating frontier language models on a novel task. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.CL TIER_1 English(EN) · Peter Potash ·

    Playing log(N)-Questions over Wikipedia Abstracts: Communication Efficiency Between Paired Frontier Models

    arXiv:2609.19113v1 Announce Type: new Abstract: We evaluate six frontier language models on the two-agent $\log(N)$-Questions game. A questioner sees $N$ Wikipedia lead paragraphs and must identify a secretly chosen target using exactly $\log_2 N$ yes/no questions. An answerer se…

RELATED ENTITIES

RELATED TOPICS