DailyReport (Claude Code): leaderboard
DailyReport (2026) tests search agents on open-ended daily information-seeking tasks about trending topics; each task is split into subtasks with cascade rubrics for instruction following, factuality and rationality, judged by Gemini 3 Flash. This board is the user preference score from 1 (unhelpful) to 4 (perfect), aggregated from subtask results by user-assigned importance, for LLMs running inside the Claude Code agent with search tools over MCP; higher is better.
Metric: User preference score (1-4: unhelpful, deficient, acceptable, perfect), aggregated from subtask results weighted by user-perceived importance; 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 July 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 (Medium) | 2.87 | #123 (GPT-5.4) |
| 2 | GLM-5 | 2.65 | #260 |
| 3 | Claude Opus 4.6 (Thinking) | 2.65 | #102 (Claude Opus 4.6) |
| 4 | Kimi K2.5 | 2.61 | #256 |
| 5 | Gemini 3.1 Pro (Preview) | 2.58 | #94 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=dailyreport-claude-code · How It Works · Data refreshed daily, snapshot 2026-11-13.