DailyReport (Claude Code) - Factuality: leaderboard
Metric: Factuality (0-1 scaled to %), the share of extracted objective claims verified correct by web search, counted only where the instruction-following rubric holds; open-ended daily search tasks on trending topics decomposed into subtasks with cascade rubrics, judged by Gemini 3 Flash; LLMs as backends of the Claude Code agent with Serper search and Jina Reader over MCP, extended thinking enabled; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 (Medium) | 81.3 |
| 2 | GLM-5 | 76.7 |
| 3 | Claude Opus 4.6 (Thinking) | 75.6 |
| 4 | Kimi K2.5 | 71.8 |
| 5 | Gemini 3.1 Pro (Preview) | 68.4 |
Interactive version: theaggregate.ai/benchmark?slug=dailyreport-claude-code-factuality · How It Works · Data refreshed daily, snapshot 2026-09-29.